{ "counts": { "by_modality": { "audio": 17, "image": 18, "video": 18 }, "documented": 52, "indexed": 1, "total_records": 53 }, "models": [ { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "flex-api", "overview" ], "value": "flux-2-flex" } ], "capability_profiles": [ { "controls": [ { "default": "true", "mode": "exact_set", "name": "prompt_upsampling", "source_ids": [ "flex-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": 5, "max": 10, "min": 1.5, "mode": "range", "name": "guidance", "source_ids": [ "flex-api" ], "state": "supported" }, { "default": 50, "max": 50, "min": 1, "mode": "range", "name": "steps", "source_ids": [ "flex-api" ], "state": "supported", "step": 1 }, { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "flex-api" ], "state": "supported", "step": 1 } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "flex-api", "text-to-image-guide" ], "state": "supported", "transport": "signed_url" } ], "endpoint": "POST /v1/flux-2-flex", "id": "text-to-image", "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "flex-api", "text-to-image-guide" ], "task": "text_to_image" }, { "controls": [ { "default": "true", "mode": "exact_set", "name": "prompt_upsampling", "source_ids": [ "flex-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": 5, "max": 10, "min": 1.5, "mode": "range", "name": "guidance", "source_ids": [ "flex-api" ], "state": "supported" }, { "default": 50, "max": 50, "min": 1, "mode": "range", "name": "steps", "source_ids": [ "flex-api" ], "state": "supported", "step": 1 }, { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "flex-api" ], "state": "supported", "step": 1 } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "flex-api", "image-editing-guide" ], "state": "supported", "transport": "signed_url" } ], "endpoint": "POST /v1/flux-2-flex", "id": "image-edit", "reference_inputs": [ { "max_count": 8, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "flex-api" ], "state": "supported" } ], "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "flex-api", "image-editing-guide" ], "task": "image_edit" } ], "conflicts": [ { "handling": "Use the explicit 1024x1024 default from the dimensions table; retain the API contradiction as provenance rather than interpreting 0.", "path": "capability_profiles.*.size.default", "source_ids": [ "flex-api", "dimensions-help" ], "summary": "The API schema gives width and height defaults of 0 despite a minimum of 64, while the dimensions table publishes a 1024x1024 default." }, { "handling": "Use 8 for the recorded REST endpoint because its live request schema exposes input_image through input_image_8; do not treat input_image_blob_path as a ninth image slot without documented semantics.", "path": "capability_profiles.image-edit.reference_inputs.image_reference.max_count", "source_ids": [ "flex-api", "overview", "image-editing-guide" ], "summary": "The model overview says the REST API accepts 8 references and the playground accepts 10, while broader editing material describes up to 10 without always naming the interface." }, { "handling": "Use USD 0.05 from the dedicated current pricing surfaces and retain the overview value as conflicting provenance.", "path": "pricing.charges.*", "source_ids": [ "pricing-live", "pricing-docs", "pricing-help", "overview" ], "summary": "The live pricing page, pricing table and help article publish USD 0.05 per megapixel, while the FLUX.2 overview comparison still says USD 0.06 per megapixel." } ], "documentation_state": "documented", "model": { "id": "black-forest-labs/flux-2-flex", "lab": "Black Forest Labs", "modality": "image", "name": "FLUX.2 [flex]", "source_ids": [ "family-model-page", "overview", "flex-api" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.05, "denomination": "USD", "id": "text-to-image-output-megapixel", "kind": "metered", "per": 1, "profile_id": "text-to-image", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.05, "denomination": "USD", "id": "image-edit-output-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.05, "denomination": "USD", "id": "image-edit-reference-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each reference image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "reference_megapixel" } ], "source_ids": [ "pricing-live", "pricing-docs", "pricing-help" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "docs-index", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ml/llms.txt" }, { "id": "family-model-page", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/models/flux-2" }, { "id": "overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_overview" }, { "id": "text-to-image-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_text_to_image" }, { "id": "image-editing-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_image_editing" }, { "id": "prompting-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_guide_flux2" }, { "id": "multi-reference-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_editing_multi_reference" }, { "id": "dimensions-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/8916739058-what-aspect-ratios-and-output-dimensions-are-supported" }, { "id": "multi-reference-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/6546682167-what-is-multi-reference-editing" }, { "id": "flex-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api-reference/models/generate-or-edit-an-image-with-flux2-%5Bflex%5D" }, { "id": "pricing-live", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/pricing?category=flux.2" }, { "id": "pricing-docs", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/quick_start/pricing" }, { "id": "pricing-help", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/7986977817-what-are-the-costs-associated-with-using-your-models" }, { "id": "integration-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api_integration/integration_guidelines" }, { "id": "mcp-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api_integration/mcp_integration" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/release-notes" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "klein-api", "overview", "openapi" ], "value": "flux-2-klein-4b" }, { "kind": "model_id", "source_ids": [ "model-card" ], "value": "black-forest-labs/FLUX.2-klein-4B" } ], "capability_profiles": [ { "controls": [ { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "klein-api", "openapi" ], "state": "supported", "step": 1 }, { "name": "prompt_upsampling", "source_ids": [ "klein-quick-help" ], "state": "unsupported" }, { "name": "grounding_search", "source_ids": [ "klein-quick-help" ], "state": "unsupported" } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "klein-api", "openapi", "text-to-image-guide" ], "state": "supported", "transport": "signed_url" }, { "endpoint": "POST /v1/flux-2-klein-4b", "id": "webhook", "source_ids": [ "openapi" ], "state": "supported", "transport": "webhook" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/flux-2-klein-4b", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "klein-api", "openapi", "text-to-image-guide" ], "task": "text_to_image", "text_input": { "source_ids": [ "klein-api", "openapi" ], "state": "unknown" } }, { "controls": [ { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "klein-api", "openapi" ], "state": "supported", "step": 1 }, { "name": "prompt_upsampling", "source_ids": [ "klein-quick-help" ], "state": "unsupported" }, { "name": "grounding_search", "source_ids": [ "klein-quick-help" ], "state": "unsupported" } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "klein-api", "openapi", "image-editing-guide" ], "state": "supported", "transport": "signed_url" }, { "endpoint": "POST /v1/flux-2-klein-4b", "id": "webhook", "source_ids": [ "openapi" ], "state": "supported", "transport": "webhook" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/flux-2-klein-4b", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 4, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "klein-api", "openapi", "klein-quick-help" ], "state": "supported" } ], "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "klein-api", "openapi", "image-editing-guide" ], "task": "image_edit", "text_input": { "source_ids": [ "klein-api", "openapi" ], "state": "unknown" } } ], "conflicts": [ { "handling": "Use the explicit 1024x1024 default from the dimensions table and retain the API contradiction rather than interpreting 0 as an output size.", "path": "capability_profiles.*.size.default", "source_ids": [ "klein-api", "openapi", "dimensions-help" ], "summary": "The live API schema gives width and height defaults of 0 despite a minimum of 64, while the dimensions table publishes a 1024x1024 default." }, { "handling": "Use the dedicated live pricing table and worked help example; retain the malformed quick-start expression as conflicting provenance.", "path": "pricing.charges.text-to-image-*", "source_ids": [ "pricing-live", "pricing-docs", "pricing-help" ], "summary": "The quick-start pricing prose contains a malformed duplicated term in its 4B example, while the live pricing table and help example agree on the first-megapixel plus additional-megapixel formula." } ], "documentation_state": "documented", "limitations": [ { "id": "not-factual-information", "source_ids": [ "model-card" ], "summary": "Black Forest Labs says the model is not intended or able to provide factual information." }, { "id": "rendered-text", "source_ids": [ "model-card" ], "summary": "Black Forest Labs says rendered text may be inaccurate or distorted." }, { "id": "training-data-bias", "source_ids": [ "model-card" ], "summary": "Black Forest Labs says the model may represent or amplify biases present in its training data." }, { "id": "four-megapixel-resizing", "source_ids": [ "dimensions-help" ], "summary": "Black Forest Labs says input or output images above 4 megapixels are automatically resized to the 4-megapixel limit." }, { "id": "signed-url-expiration", "source_ids": [ "image-editing-guide" ], "summary": "Black Forest Labs says signed result URLs expire after ten minutes." } ], "model": { "id": "black-forest-labs/flux-2-klein-4b", "lab": "Black Forest Labs", "modality": "image", "name": "FLUX.2 [klein] 4B", "source_ids": [ "model-page", "overview", "klein-api", "release-notes" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.014, "applies_when": [ "first output megapixel" ], "denomination": "USD", "id": "text-to-image-first-output-megapixel", "kind": "metered", "per": 1, "profile_id": "text-to-image", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.001, "applies_when": [ "each output megapixel after the first" ], "denomination": "USD", "id": "text-to-image-additional-output-megapixel", "kind": "metered", "per": 1, "profile_id": "text-to-image", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.014, "applies_when": [ "first output megapixel" ], "denomination": "USD", "id": "image-edit-first-output-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.001, "applies_when": [ "each output megapixel after the first" ], "denomination": "USD", "id": "image-edit-additional-output-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.001, "denomination": "USD", "id": "image-edit-reference-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each reference image is rounded up separately for billing; 1 megapixel is counted as 1024x1024, so every reference counts as at least 1 megapixel.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "reference_megapixel" } ], "source_ids": [ "pricing-live", "pricing-docs", "pricing-help" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "docs-index", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/llms.txt" }, { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/models/flux-2-klein" }, { "id": "overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_overview" }, { "id": "text-to-image-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_text_to_image" }, { "id": "image-editing-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_image_editing" }, { "id": "multi-reference-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_editing_multi_reference" }, { "id": "unified-reference-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_unified_reference" }, { "id": "dimensions-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/8916739058-what-aspect-ratios-and-output-dimensions-are-supported" }, { "id": "klein-quick-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/7592221790-how-do-i-generate-quickly-with-flux-2-klein" }, { "id": "klein-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api-reference/models/generate-or-edit-an-image-with-flux2-%5Bklein%5D-4b" }, { "id": "openapi", "kind": "api_schema", "retrieved_on": "2026-08-10", "url": "https://api.bfl.ai/openapi.json" }, { "id": "pricing-live", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/pricing?category=flux.2" }, { "id": "pricing-docs", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/quick_start/pricing" }, { "id": "pricing-help", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/7986977817-what-are-the-costs-associated-with-using-your-models" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/release-notes" }, { "id": "model-card", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://huggingface.co/black-forest-labs/FLUX.2-klein-4B" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "klein-api", "overview", "openapi" ], "value": "flux-2-klein-9b" }, { "kind": "model_id", "source_ids": [ "model-card" ], "value": "black-forest-labs/FLUX.2-klein-9B" } ], "capability_profiles": [ { "controls": [ { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "klein-api", "openapi" ], "state": "supported", "step": 1 }, { "name": "prompt_upsampling", "source_ids": [ "klein-quick-help" ], "state": "unsupported" }, { "name": "grounding_search", "source_ids": [ "klein-quick-help" ], "state": "unsupported" } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "klein-api", "openapi", "text-to-image-guide" ], "state": "supported", "transport": "signed_url" }, { "endpoint": "POST /v1/flux-2-klein-9b", "id": "webhook", "source_ids": [ "openapi" ], "state": "supported", "transport": "webhook" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/flux-2-klein-9b", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "klein-api", "openapi", "text-to-image-guide" ], "task": "text_to_image", "text_input": { "source_ids": [ "klein-api", "openapi" ], "state": "unknown" } }, { "controls": [ { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "klein-api", "openapi" ], "state": "supported", "step": 1 }, { "name": "prompt_upsampling", "source_ids": [ "klein-quick-help" ], "state": "unsupported" }, { "name": "grounding_search", "source_ids": [ "klein-quick-help" ], "state": "unsupported" } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "klein-api", "openapi", "image-editing-guide" ], "state": "supported", "transport": "signed_url" }, { "endpoint": "POST /v1/flux-2-klein-9b", "id": "webhook", "source_ids": [ "openapi" ], "state": "supported", "transport": "webhook" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/flux-2-klein-9b", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 4, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "klein-api", "openapi", "klein-quick-help" ], "state": "supported" } ], "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "klein-api", "openapi", "image-editing-guide" ], "task": "image_edit", "text_input": { "source_ids": [ "klein-api", "openapi" ], "state": "unknown" } } ], "conflicts": [ { "handling": "Use the explicit 1024x1024 default from the dimensions table and retain the API contradiction rather than interpreting 0 as an output size.", "path": "capability_profiles.*.size.default", "source_ids": [ "klein-api", "openapi", "dimensions-help" ], "summary": "The live API schema gives width and height defaults of 0 despite a minimum of 64, while the dimensions table publishes a 1024x1024 default." }, { "handling": "Record only the fixed endpoint in this model record and do not collapse the preview endpoint into an alias.", "path": "api_identifiers.flux-2-klein-9b-preview", "source_ids": [ "overview", "klein-api", "preview-api", "openapi" ], "summary": "BFL documents flux-2-klein-9b as a fixed snapshot and flux-2-klein-9b-preview as a mutable endpoint whose underlying weights change." } ], "documentation_state": "documented", "limitations": [ { "id": "not-factual-information", "source_ids": [ "model-card" ], "summary": "Black Forest Labs says the model is not intended or able to provide factual information." }, { "id": "rendered-text", "source_ids": [ "model-card" ], "summary": "Black Forest Labs says rendered text may be inaccurate or distorted." }, { "id": "training-data-bias", "source_ids": [ "model-card" ], "summary": "Black Forest Labs says the model may represent or amplify biases present in its training data." }, { "id": "prompt-matching", "source_ids": [ "model-card" ], "summary": "Black Forest Labs says the model may fail to match the prompt." }, { "id": "prompting-style-dependence", "source_ids": [ "model-card" ], "summary": "Black Forest Labs says prompt following is strongly influenced by prompting style." }, { "id": "four-megapixel-resizing", "source_ids": [ "dimensions-help" ], "summary": "Black Forest Labs says input or output images above 4 megapixels are automatically resized to the 4-megapixel limit." }, { "id": "signed-url-expiration", "source_ids": [ "image-editing-guide" ], "summary": "Black Forest Labs says signed result URLs expire after ten minutes." } ], "model": { "id": "black-forest-labs/flux-2-klein-9b", "lab": "Black Forest Labs", "modality": "image", "name": "FLUX.2 [klein] 9B", "source_ids": [ "model-page", "overview", "klein-api", "release-notes" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.015, "applies_when": [ "first output megapixel" ], "denomination": "USD", "id": "text-to-image-first-output-megapixel", "kind": "metered", "per": 1, "profile_id": "text-to-image", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.002, "applies_when": [ "each output megapixel after the first" ], "denomination": "USD", "id": "text-to-image-additional-output-megapixel", "kind": "metered", "per": 1, "profile_id": "text-to-image", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.015, "applies_when": [ "first output megapixel" ], "denomination": "USD", "id": "image-edit-first-output-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.002, "applies_when": [ "each output megapixel after the first" ], "denomination": "USD", "id": "image-edit-additional-output-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.002, "denomination": "USD", "id": "image-edit-reference-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each reference image is rounded up separately for billing; 1 megapixel is counted as 1024x1024, so every reference counts as at least 1 megapixel.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "reference_megapixel" } ], "source_ids": [ "pricing-live", "pricing-docs", "pricing-help" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "docs-index", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/llms.txt" }, { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/models/flux-2-klein" }, { "id": "overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_overview" }, { "id": "text-to-image-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_text_to_image" }, { "id": "image-editing-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_image_editing" }, { "id": "multi-reference-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_editing_multi_reference" }, { "id": "unified-reference-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_unified_reference" }, { "id": "dimensions-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/8916739058-what-aspect-ratios-and-output-dimensions-are-supported" }, { "id": "klein-quick-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/7592221790-how-do-i-generate-quickly-with-flux-2-klein" }, { "id": "klein-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api-reference/models/generate-or-edit-an-image-with-flux2-%5Bklein%5D-9b" }, { "id": "preview-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api-reference/models/generate-or-edit-an-image-with-flux2-%5Bklein%5D-9b-preview" }, { "id": "openapi", "kind": "api_schema", "retrieved_on": "2026-08-10", "url": "https://api.bfl.ai/openapi.json" }, { "id": "pricing-live", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/pricing?category=flux.2" }, { "id": "pricing-docs", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/quick_start/pricing" }, { "id": "pricing-help", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/7986977817-what-are-the-costs-associated-with-using-your-models" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/release-notes" }, { "id": "model-card", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://huggingface.co/black-forest-labs/FLUX.2-klein-9B" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "max-api", "overview" ], "value": "flux-2-max" } ], "capability_profiles": [ { "controls": [ { "default": "false", "mode": "exact_set", "name": "disable_pup", "source_ids": [ "max-api" ], "state": "supported", "values": [ "false", "true" ] }, { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "max-api" ], "state": "supported", "step": 1 } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "max-api", "text-to-image-guide" ], "state": "supported", "transport": "signed_url" } ], "endpoint": "POST /v1/flux-2-max", "id": "text-to-image", "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "max-api", "text-to-image-guide" ], "task": "text_to_image" }, { "controls": [ { "default": "false", "mode": "exact_set", "name": "disable_pup", "source_ids": [ "max-api" ], "state": "supported", "values": [ "false", "true" ] }, { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "max-api" ], "state": "supported", "step": 1 } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "max-api", "image-editing-guide" ], "state": "supported", "transport": "signed_url" } ], "endpoint": "POST /v1/flux-2-max", "id": "image-edit", "reference_inputs": [ { "max_count": 8, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "max-api" ], "state": "supported" } ], "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "max-api", "image-editing-guide" ], "task": "image_edit" } ], "conflicts": [ { "handling": "Use the explicit 1024x1024 default from the dimensions table; retain the API contradiction as provenance rather than interpreting 0.", "path": "capability_profiles.*.size.default", "source_ids": [ "max-api", "dimensions-help" ], "summary": "The API schema gives width and height defaults of 0 despite a minimum of 64, while the dimensions table publishes a 1024x1024 default." }, { "handling": "Use 8 for the recorded REST endpoint because its live request schema exposes input_image through input_image_8; do not apply a playground limit to the API.", "path": "capability_profiles.image-edit.reference_inputs.image_reference.max_count", "source_ids": [ "max-api", "overview", "max-model-page", "image-editing-guide" ], "summary": "The model overview says the REST API accepts 8 references and the playground accepts 10, while the Max model page and broader editing material describe multiple references without exposing another REST parameter." } ], "documentation_state": "documented", "model": { "id": "black-forest-labs/flux-2-max", "lab": "Black Forest Labs", "modality": "image", "name": "FLUX.2 [max]", "source_ids": [ "max-model-page", "overview", "max-api" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.07, "applies_when": [ "first output megapixel" ], "denomination": "USD", "id": "text-to-image-first-output-megapixel", "kind": "metered", "per": 1, "profile_id": "text-to-image", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.03, "applies_when": [ "each output megapixel after the first" ], "denomination": "USD", "id": "text-to-image-additional-output-megapixel", "kind": "metered", "per": 1, "profile_id": "text-to-image", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.07, "applies_when": [ "first output megapixel" ], "denomination": "USD", "id": "image-edit-first-output-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.03, "applies_when": [ "each output megapixel after the first" ], "denomination": "USD", "id": "image-edit-additional-output-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.03, "denomination": "USD", "id": "image-edit-reference-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each reference image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "reference_megapixel" } ], "source_ids": [ "pricing-live", "pricing-docs", "pricing-help" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "docs-index", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ml/llms.txt" }, { "id": "max-model-page", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/models/flux-2-max" }, { "id": "family-model-page", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/models/flux-2" }, { "id": "overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_overview" }, { "id": "text-to-image-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_text_to_image" }, { "id": "image-editing-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_image_editing" }, { "id": "prompting-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_guide_flux2" }, { "id": "multi-reference-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_editing_multi_reference" }, { "id": "dimensions-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/8916739058-what-aspect-ratios-and-output-dimensions-are-supported" }, { "id": "multi-reference-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/6546682167-what-is-multi-reference-editing" }, { "id": "max-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api-reference/models/generate-or-edit-an-image-with-flux2-%5Bmax%5D" }, { "id": "pricing-live", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/pricing?category=flux.2" }, { "id": "pricing-docs", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/quick_start/pricing" }, { "id": "pricing-help", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/7986977817-what-are-the-costs-associated-with-using-your-models" }, { "id": "integration-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api_integration/integration_guidelines" }, { "id": "mcp-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api_integration/mcp_integration" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/release-notes" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "pro-api", "overview" ], "value": "flux-2-pro" } ], "capability_profiles": [ { "controls": [ { "default": "false", "mode": "exact_set", "name": "disable_pup", "source_ids": [ "pro-api" ], "state": "supported", "values": [ "false", "true" ] }, { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "pro-api" ], "state": "supported", "step": 1 } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "pro-api", "text-to-image-guide" ], "state": "supported", "transport": "signed_url" } ], "endpoint": "POST /v1/flux-2-pro", "id": "text-to-image", "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "pro-api", "text-to-image-guide" ], "task": "text_to_image" }, { "controls": [ { "default": "false", "mode": "exact_set", "name": "disable_pup", "source_ids": [ "pro-api" ], "state": "supported", "values": [ "false", "true" ] }, { "default": 2, "max": 5, "min": 0, "mode": "range", "name": "safety_tolerance", "source_ids": [ "pro-api" ], "state": "supported", "step": 1 } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "GET {polling_url}", "formats": [ "jpeg", "png", "webp" ], "id": "signed-url", "source_ids": [ "pro-api", "image-editing-guide" ], "state": "supported", "transport": "signed_url" } ], "endpoint": "POST /v1/flux-2-pro", "id": "image-edit", "reference_inputs": [ { "constraints": [ "Input and output images share a 9-megapixel total limit.", "At a 1-megapixel output, up to 8 reference images are allowed.", "At a 2-megapixel output, up to 7 reference images are allowed." ], "max_count": 8, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "pro-api", "multi-reference-guide" ], "state": "supported" } ], "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 64, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 64 }, { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 880, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "dimensions-help" ], "unit": "pixel", "width": 2048 } ], "max_total_pixels": 4194304, "min_total_pixels": 4096, "mode": "range", "source_ids": [ "dimensions-help" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "pro-api", "image-editing-guide" ], "task": "image_edit" } ], "conflicts": [ { "handling": "Use the explicit 1024x1024 default from the dimensions table; retain the API contradiction as provenance rather than interpreting 0.", "path": "capability_profiles.*.size.default", "source_ids": [ "pro-api", "dimensions-help" ], "summary": "The API schema gives width and height defaults of 0 despite a minimum of 64, while the dimensions table publishes a 1024x1024 default." }, { "handling": "Use 8 for the recorded REST endpoint because its live request schema exposes input_image through input_image_8; do not apply the playground limit to the API.", "path": "capability_profiles.image-edit.reference_inputs.image_reference.max_count", "source_ids": [ "pro-api", "overview", "image-editing-guide" ], "summary": "The model overview says the REST API accepts 8 references and the playground accepts 10, while broader editing material describes up to 10 without always naming the interface." }, { "handling": "Record only the fixed flux-2-pro endpoint here and do not collapse the preview endpoint into an alias until its changing release identity can be represented safely.", "path": "api_identifiers.flux-2-pro-preview", "source_ids": [ "overview", "pro-api", "pro-preview-api" ], "summary": "BFL documents flux-2-pro as a fixed snapshot and flux-2-pro-preview as a mutable latest endpoint; their contracts match but their underlying weights differ." } ], "documentation_state": "documented", "model": { "id": "black-forest-labs/flux-2-pro", "lab": "Black Forest Labs", "modality": "image", "name": "FLUX.2 [pro]", "source_ids": [ "family-model-page", "overview", "pro-api" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.03, "applies_when": [ "first output megapixel" ], "denomination": "USD", "id": "text-to-image-first-output-megapixel", "kind": "metered", "per": 1, "profile_id": "text-to-image", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.015, "applies_when": [ "each output megapixel after the first" ], "denomination": "USD", "id": "text-to-image-additional-output-megapixel", "kind": "metered", "per": 1, "profile_id": "text-to-image", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.03, "applies_when": [ "first output megapixel" ], "denomination": "USD", "id": "image-edit-first-output-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.015, "applies_when": [ "each output megapixel after the first" ], "denomination": "USD", "id": "image-edit-additional-output-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "output_megapixel" }, { "amount": 0.015, "denomination": "USD", "id": "image-edit-reference-megapixel", "kind": "metered", "per": 1, "profile_id": "image-edit", "qualifier": "Each reference image is rounded up separately for billing; 1 megapixel is counted as 1024x1024.", "source_ids": [ "pricing-live", "pricing-help" ], "state": "known", "unit": "reference_megapixel" } ], "source_ids": [ "pricing-live", "pricing-docs", "pricing-help" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "docs-index", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ml/llms.txt" }, { "id": "family-model-page", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/models/flux-2" }, { "id": "overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_overview" }, { "id": "text-to-image-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_text_to_image" }, { "id": "image-editing-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/flux_2/flux2_image_editing" }, { "id": "prompting-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_guide_flux2" }, { "id": "multi-reference-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/guides/prompting_editing_multi_reference" }, { "id": "dimensions-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/8916739058-what-aspect-ratios-and-output-dimensions-are-supported" }, { "id": "multi-reference-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/6546682167-what-is-multi-reference-editing" }, { "id": "pro-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api-reference/models/generate-or-edit-an-image-with-flux2-%5Bpro%5D" }, { "id": "pro-preview-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api-reference/models/generate-or-edit-an-image-with-flux2-%5Bpro%5D-preview" }, { "id": "pricing-live", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://bfl.ai/pricing?category=flux.2" }, { "id": "pricing-docs", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/quick_start/pricing" }, { "id": "pricing-help", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://help.bfl.ai/articles/7986977817-what-are-the-costs-associated-with-using-your-models" }, { "id": "integration-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api_integration/integration_guidelines" }, { "id": "mcp-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/api_integration/mcp_integration" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://docs.bfl.ai/release-notes" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "openapi" ], "value": "flux-3-video" }, { "kind": "version_selector", "source_ids": [ "openapi" ], "value": "latest" } ], "capability_profiles": [ { "api_mode": "t2v", "api_mode_aliases": [ "text-to-video" ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "signed-url", "source_ids": [ "video-guide" ], "state": "supported", "transport": "signed_url" } ], "duration": { "automatic": true, "max": 20, "min": 5, "mode": "range", "source_ids": [ "openapi" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/flux-3-video", "frame_rate": { "mode": "exact_set", "source_ids": [ "overview" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "text-to-video", "native_audio": { "default": true, "source_ids": [ "model-page", "openapi" ], "state": "supported" }, "reference_inputs": [ { "media_type": "audio", "role": "audio_reference", "source_ids": [ "overview", "openapi" ], "state": "unsupported" } ], "size": { "automatic": true, "default": "auto", "mode": "exact_set", "options": [ { "aspect_ratios": [ "21:9", "2:1", "16:9", "4:3", "1:1", "3:4", "9:16" ], "id": "hd", "label": "HD / 720p", "max_megapixels": 1, "render_modes": [ "standard", "draft" ], "source_ids": [ "model-page", "overview", "openapi" ] }, { "aspect_ratios": [ "21:9", "2:1", "16:9", "4:3", "1:1", "3:4", "9:16" ], "examples": [ { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "overview" ], "unit": "pixel", "width": 1920 } ], "id": "fhd", "label": "Full HD / 1080p", "max_megapixels": 2, "render_modes": [ "standard" ], "source_ids": [ "model-page", "overview", "openapi" ] } ], "source_ids": [ "overview", "openapi" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "openapi", "api-reference" ], "task": "text_to_video", "variants": [ "standard", "draft" ] }, { "api_mode": "i2v", "api_mode_aliases": [ "image-continuation" ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "signed-url", "source_ids": [ "video-guide" ], "state": "supported", "transport": "signed_url" } ], "duration": { "automatic": true, "max": 20, "min": 5, "mode": "range", "source_ids": [ "openapi" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/flux-3-video", "frame_rate": { "mode": "exact_set", "source_ids": [ "overview" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "image-to-video", "native_audio": { "default": true, "source_ids": [ "model-page", "openapi" ], "state": "supported" }, "reference_inputs": [ { "encodings": [ "https_url", "base64" ], "max_count": 10, "media_type": "image", "min_count": 1, "position_roles": [ "start_image", "intermediate_keyframe", "end_image" ], "role": "keyframe_sequence", "source_ids": [ "openapi", "video-guide" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "overview", "openapi" ], "state": "unsupported" } ], "size": { "automatic": true, "default": "auto", "mode": "exact_set", "options": [ { "aspect_ratios": [ "21:9", "2:1", "16:9", "4:3", "1:1", "3:4", "9:16" ], "id": "hd", "label": "HD / 720p", "max_megapixels": 1, "render_modes": [ "standard", "draft" ], "source_ids": [ "model-page", "overview", "openapi" ] }, { "aspect_ratios": [ "21:9", "2:1", "16:9", "4:3", "1:1", "3:4", "9:16" ], "examples": [ { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "overview" ], "unit": "pixel", "width": 1920 } ], "id": "fhd", "label": "Full HD / 1080p", "max_megapixels": 2, "render_modes": [ "standard" ], "source_ids": [ "model-page", "overview", "openapi" ] } ], "source_ids": [ "overview", "openapi" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "openapi", "api-reference" ], "task": "image_to_video", "variants": [ "standard", "draft" ] }, { "api_mode": "v2v", "api_mode_aliases": [ "video-continuation" ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "signed-url", "source_ids": [ "video-guide" ], "state": "supported", "transport": "signed_url" } ], "duration": { "automatic": true, "max": 20, "min": 5, "mode": "range", "source_ids": [ "openapi" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/flux-3-video", "frame_rate": { "mode": "exact_set", "source_ids": [ "overview" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "video-continuation", "native_audio": { "default": true, "source_ids": [ "model-page", "openapi" ], "state": "supported" }, "reference_inputs": [ { "duration_unit": "second", "encodings": [ "https_url", "base64" ], "formats": [ "mp4" ], "max_count": 1, "max_duration": 4, "media_type": "video", "min_count": 1, "role": "start_video", "source_ids": [ "launch", "openapi" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "overview", "openapi" ], "state": "unsupported" } ], "size": { "automatic": true, "default": "auto", "mode": "exact_set", "options": [ { "aspect_ratios": [ "21:9", "2:1", "16:9", "4:3", "1:1", "3:4", "9:16" ], "id": "hd", "label": "HD / 720p", "max_megapixels": 1, "render_modes": [ "standard", "draft" ], "source_ids": [ "model-page", "overview", "openapi" ] }, { "aspect_ratios": [ "21:9", "2:1", "16:9", "4:3", "1:1", "3:4", "9:16" ], "examples": [ { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "overview" ], "unit": "pixel", "width": 1920 } ], "id": "fhd", "label": "Full HD / 1080p", "max_megapixels": 2, "render_modes": [ "standard" ], "source_ids": [ "model-page", "overview", "openapi" ] } ], "source_ids": [ "overview", "openapi" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "openapi", "api-reference" ], "task": "video_continuation", "variants": [ "standard", "draft" ] }, { "api_mode": "draft_enhance", "api_mode_aliases": [ "draft-enhance" ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "signed-url", "source_ids": [ "video-guide" ], "state": "supported", "transport": "signed_url" } ], "duration": { "max": 20, "min": 5, "mode": "range", "source_ids": [ "openapi", "model-page" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/flux-3-video", "frame_rate": { "mode": "exact_set", "source_ids": [ "overview" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "draft-enhancement", "native_audio": { "source_ids": [ "openapi", "model-page" ], "state": "unknown" }, "reference_inputs": [ { "encodings": [ "https_url", "base64" ], "formats": [ "bin" ], "max_count": 1, "media_type": "binary", "min_count": 1, "role": "draft_cache", "source_ids": [ "openapi", "model-page" ], "state": "supported" } ], "size": { "default": "fhd", "mode": "exact_set", "options": [ { "id": "hd", "label": "HD / 720p", "max_megapixels": 1, "source_ids": [ "model-page", "overview", "openapi" ] }, { "examples": [ { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "overview" ], "unit": "pixel", "width": 1920 } ], "id": "fhd", "label": "Full HD / 1080p", "max_megapixels": 2, "source_ids": [ "model-page", "overview", "openapi" ] } ], "source_ids": [ "openapi" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "openapi", "model-page" ], "task": "draft_enhancement" } ], "conflicts": [ { "handling": "Use FLUX 3 Video for this video-model record; do not collapse future FLUX 3 modality releases into it without new source review.", "path": "model.name", "source_ids": [ "launch", "model-page" ], "summary": "BFL uses FLUX 3 for the multimodal family heading and FLUX 3 Video for the released video product and API capability." }, { "handling": "Use available from the dated 2026-08-04 launch and retain both sources.", "path": "model.status", "source_ids": [ "launch", "overview" ], "summary": "The dated launch announcement says generally available; the undated overview still says preview." }, { "handling": "Use 20 from the callable API contract and keep the overview as conflicting provenance.", "path": "capability_profiles.video-continuation.duration.max", "source_ids": [ "openapi", "overview" ], "summary": "The live OpenAPI allows 5-20 seconds; the overview table says 5-15 seconds." }, { "handling": "Use the matching values from the current calculator and model FAQ.", "path": "pricing.charges.v2v-standard-hd,pricing.charges.v2v-standard-fhd", "source_ids": [ "pricing", "model-page", "docs-pricing" ], "summary": "The main pricing page and model FAQ publish USD 0.41/0.53 per second; the docs pricing table publishes USD 0.43/0.54." }, { "handling": "Preserve both the published tier label and the exact example; do not normalize it to 1920x1080.", "path": "capability_profiles.*.size.options.fhd", "source_ids": [ "overview" ], "summary": "BFL labels the tier Full HD / 1080p but its exact 16:9 example is 1920x1088." }, { "handling": "Keep HD enhancement pricing unknown.", "path": "pricing.charges.draft-enhance-hd", "source_ids": [ "openapi", "model-page" ], "summary": "The API permits HD or FHD enhancement, while the model FAQ only states the corresponding standard FHD price." } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "English" }, { "name": "Chinese" }, { "name": "Spanish" }, { "name": "French" }, { "name": "German" }, { "name": "Japanese" }, { "name": "Portuguese" }, { "name": "Russian" }, { "name": "Italian" }, { "name": "Indonesian" }, { "name": "Turkish" }, { "name": "Hindi" }, { "name": "Punjabi" } ], "list_completeness": "non_exhaustive", "listed_count": 13, "published_label": "multilingual; thirteen languages are named and more are claimed", "scope": "native_audio", "source_ids": [ "launch" ], "state": "supported" }, "model": { "id": "black-forest-labs/flux-3-video", "lab": "Black Forest Labs", "modality": "video", "name": "FLUX 3 Video", "source_ids": [ "launch", "model-page" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.06, "applies_when": [ "task=text_to_video", "render=draft", "size=hd" ], "denomination": "USD", "id": "t2v-draft-hd", "kind": "metered", "per": 1, "source_ids": [ "pricing", "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.06, "applies_when": [ "task=image_to_video", "render=draft", "size=hd" ], "denomination": "USD", "id": "i2v-draft-hd", "kind": "metered", "per": 1, "source_ids": [ "pricing", "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.17, "applies_when": [ "task=text_to_video", "render=standard", "size=hd" ], "denomination": "USD", "id": "t2v-standard-hd", "kind": "metered", "per": 1, "source_ids": [ "pricing", "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.17, "applies_when": [ "task=image_to_video", "render=standard", "size=hd" ], "denomination": "USD", "id": "i2v-standard-hd", "kind": "metered", "per": 1, "source_ids": [ "pricing", "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.29, "applies_when": [ "task=text_to_video", "render=standard", "size=fhd" ], "denomination": "USD", "id": "t2v-standard-fhd", "kind": "metered", "per": 1, "source_ids": [ "pricing", "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.29, "applies_when": [ "task=image_to_video", "render=standard", "size=fhd" ], "denomination": "USD", "id": "i2v-standard-fhd", "kind": "metered", "per": 1, "source_ids": [ "pricing", "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.12, "applies_when": [ "task=video_continuation", "render=draft", "size=hd" ], "denomination": "USD", "id": "v2v-draft-hd", "kind": "metered", "per": 1, "source_ids": [ "pricing", "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.41, "applies_when": [ "task=video_continuation", "render=standard", "size=hd" ], "denomination": "USD", "id": "v2v-standard-hd", "kind": "metered", "per": 1, "source_ids": [ "pricing", "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.53, "applies_when": [ "task=video_continuation", "render=standard", "size=fhd" ], "denomination": "USD", "id": "v2v-standard-fhd", "kind": "metered", "per": 1, "source_ids": [ "pricing", "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.29, "applies_when": [ "task=draft_enhancement", "origin_task=text_to_video", "size=fhd" ], "denomination": "USD", "id": "draft-enhance-from-t2v-fhd", "kind": "metered", "per": 1, "source_ids": [ "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.29, "applies_when": [ "task=draft_enhancement", "origin_task=image_to_video", "size=fhd" ], "denomination": "USD", "id": "draft-enhance-from-i2v-fhd", "kind": "metered", "per": 1, "source_ids": [ "model-page" ], "state": "known", "unit": "output_second" }, { "amount": 0.53, "applies_when": [ "task=draft_enhancement", "origin_task=video_continuation", "size=fhd" ], "denomination": "USD", "id": "draft-enhance-from-v2v-fhd", "kind": "metered", "per": 1, "source_ids": [ "model-page" ], "state": "known", "unit": "output_second" }, { "applies_when": [ "task=draft_enhancement", "size=hd" ], "id": "draft-enhance-hd", "source_ids": [ "openapi", "model-page" ], "state": "unknown" }, { "amount": 0, "applies_when": [ "native_audio=true" ], "denomination": "USD", "id": "native-audio", "kind": "metered", "per": 1, "qualifier": "included", "source_ids": [ "model-page" ], "state": "known", "unit": "output_second" } ], "source_ids": [ "pricing", "model-page", "docs-pricing" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "launch", "kind": "release_note", "retrieved_on": "2026-08-09", "url": "https://bfl.ai/blog/flux-3-video" }, { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://bfl.ai/models/flux-3" }, { "id": "overview", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://docs.bfl.ai/flux_3/flux3_overview" }, { "id": "video-guide", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://docs.bfl.ai/flux_3/flux3_video" }, { "id": "api-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://docs.bfl.ai/api-reference/utility/generate-a-video-with-flux-3" }, { "id": "openapi", "kind": "api_schema", "retrieved_on": "2026-08-09", "url": "https://api.bfl.ai/openapi.json" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-09", "url": "https://bfl.ai/pricing" }, { "id": "docs-pricing", "kind": "pricing", "retrieved_on": "2026-08-09", "url": "https://docs.bfl.ai/quick_start/pricing" } ] }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "series-tutorial", "model-list", "pricing" ], "value": "dreamina-seedance-2-0-260128" } ], "capability_profiles": [ { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "text-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 496, "source_ids": [ "video-api" ], "unit": "pixel", "width": 864 }, { "aspect_ratio": "4:3", "height": 560, "source_ids": [ "video-api" ], "unit": "pixel", "width": 752 }, { "aspect_ratio": "1:1", "height": 640, "source_ids": [ "video-api" ], "unit": "pixel", "width": 640 }, { "aspect_ratio": "3:4", "height": 752, "source_ids": [ "video-api" ], "unit": "pixel", "width": 560 }, { "aspect_ratio": "9:16", "height": 864, "source_ids": [ "video-api" ], "unit": "pixel", "width": 496 }, { "aspect_ratio": "21:9", "height": 432, "source_ids": [ "video-api" ], "unit": "pixel", "width": 992 } ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1280 }, { "aspect_ratio": "4:3", "height": 834, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1112 }, { "aspect_ratio": "1:1", "height": 960, "source_ids": [ "video-api" ], "unit": "pixel", "width": 960 }, { "aspect_ratio": "3:4", "height": 1112, "source_ids": [ "video-api" ], "unit": "pixel", "width": 834 }, { "aspect_ratio": "9:16", "height": 1280, "source_ids": [ "video-api" ], "unit": "pixel", "width": 720 }, { "aspect_ratio": "21:9", "height": 630, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1470 } ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 1080, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "4:3", "height": 1248, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1664 }, { "aspect_ratio": "1:1", "height": 1440, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1440 }, { "aspect_ratio": "3:4", "height": 1664, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1248 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1080 }, { "aspect_ratio": "21:9", "height": 946, "source_ids": [ "video-api" ], "unit": "pixel", "width": 2206 } ], "id": "1080p", "label": "1080p", "source_ids": [ "video-api", "series-tutorial", "release-notes" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 2160, "source_ids": [ "video-api" ], "unit": "pixel", "width": 3840 }, { "aspect_ratio": "4:3", "height": 2494, "source_ids": [ "video-api" ], "unit": "pixel", "width": 3326 }, { "aspect_ratio": "1:1", "height": 2880, "source_ids": [ "video-api" ], "unit": "pixel", "width": 2880 }, { "aspect_ratio": "3:4", "height": 3326, "source_ids": [ "video-api" ], "unit": "pixel", "width": 2494 }, { "aspect_ratio": "9:16", "height": 3840, "source_ids": [ "video-api" ], "unit": "pixel", "width": 2160 }, { "aspect_ratio": "21:9", "height": 1886, "source_ids": [ "video-api" ], "unit": "pixel", "width": 4398 } ], "id": "4k", "label": "4K (10-bit encoding)", "source_ids": [ "model-list", "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial", "release-notes" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial", "prompt-guide" ], "task": "text_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-frame-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api", "release-notes" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "1080p", "label": "1080p", "source_ids": [ "video-api", "series-tutorial", "release-notes" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "4k", "label": "4K (10-bit encoding)", "source_ids": [ "model-list", "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial", "release-notes" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial" ], "task": "image_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-last-frame-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api", "release-notes" ], "state": "supported" }, { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64", "cropped_to_start_image_ratio_when_ratios_differ=true" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "end_image", "source_ids": [ "video-api", "release-notes" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "1080p", "label": "1080p", "source_ids": [ "video-api", "series-tutorial", "release-notes" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "4k", "label": "4K (10-bit encoding)", "source_ids": [ "model-list", "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial", "release-notes" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial" ], "task": "first_last_frame_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "omni-reference-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 9, "media_type": "image", "min_count": 0, "role": "image_reference", "source_ids": [ "video-api", "series-tutorial", "release-notes" ], "state": "supported" }, { "constraints": [ "duration_seconds>=2", "aggregate_duration_seconds<=15", "resolution_tiers=480p,720p,1080p,4k", "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "total_pixels>=409600", "total_pixels<=8295044", "size_megabytes<=200", "frame_rate_fps>=24", "frame_rate_fps<=60", "video_codecs=H.264/AVC,H.265/HEVC", "audio_codecs=AAC,MP3" ], "duration_unit": "second", "encodings": [ "url", "asset_id" ], "formats": [ "mp4", "mov" ], "max_count": 3, "max_duration": 15, "media_type": "video", "min_count": 0, "role": "video_reference", "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, { "constraints": [ "duration_seconds>=2", "aggregate_duration_seconds<=15", "size_megabytes<=15", "request_body_megabytes<=64", "audio_only_input=false" ], "duration_unit": "second", "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "wav", "mp3" ], "max_count": 3, "max_duration": 15, "media_type": "audio", "min_count": 0, "role": "audio_reference", "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "1080p", "label": "1080p", "source_ids": [ "video-api", "series-tutorial", "release-notes" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "4k", "label": "4K (10-bit encoding)", "source_ids": [ "model-list", "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial", "release-notes" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial", "prompt-guide" ], "task": "omni_reference_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "English" }, { "name": "Spanish" }, { "name": "Indonesian" }, { "name": "Portuguese" }, { "name": "Japanese" } ], "listed_count": 5, "published_label": "English, Spanish, Indonesian, Portuguese, and Japanese", "scope": "prompt_input", "source_ids": [ "video-api" ], "state": "supported" }, "limitations": [ { "id": "direct-real-human-face-input", "source_ids": [ "video-api" ], "summary": "BytePlus states that Seedance 2.0 series models do not support directly uploaded reference images or videos containing real human faces; trusted generated outputs, preset digital characters, or authorized real-person assets are the documented alternatives." }, { "id": "generated-audio-mono", "source_ids": [ "video-api" ], "summary": "BytePlus states that generated videos with audio use mono output regardless of the input audio channel count." }, { "id": "precise-timing-instability", "source_ids": [ "prompt-guide" ], "summary": "BytePlus states that precise prompt timing such as 0–3 second segments is unstable and that forcing strict segment durations may cause abnormal generation results." }, { "id": "narration-end-noise", "source_ids": [ "prompt-guide" ], "summary": "BytePlus states that videos with narration are likely to contain abrupt clicks or cut-off noise at the end." } ], "model": { "aliases": [ "Seedance 2.0" ], "id": "bytedance/dreamina-seedance-2-0", "lab": "ByteDance", "modality": "video", "name": "Dreamina Seedance 2.0", "source_ids": [ "seed-model-page", "seed-launch", "series-tutorial", "model-list" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 7, "applies_when": [ "service_tier=default", "resolution=480p", "input_video=false" ], "denomination": "USD", "id": "online-480p-without-video-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 4.3, "applies_when": [ "service_tier=default", "resolution=480p", "input_video=true" ], "denomination": "USD", "id": "online-480p-with-video-input", "kind": "metered", "per": 1000000, "qualifier": "A minimum token-consumption rule applies when the input includes video; the threshold depends on resolution, aspect ratio, and output duration.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 7, "applies_when": [ "service_tier=default", "resolution=720p", "input_video=false" ], "denomination": "USD", "id": "online-720p-without-video-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 4.3, "applies_when": [ "service_tier=default", "resolution=720p", "input_video=true" ], "denomination": "USD", "id": "online-720p-with-video-input", "kind": "metered", "per": 1000000, "qualifier": "A minimum token-consumption rule applies when the input includes video; the threshold depends on resolution, aspect ratio, and output duration.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 7.7, "applies_when": [ "service_tier=default", "resolution=1080p", "input_video=false" ], "denomination": "USD", "id": "online-1080p-without-video-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 4.7, "applies_when": [ "service_tier=default", "resolution=1080p", "input_video=true" ], "denomination": "USD", "id": "online-1080p-with-video-input", "kind": "metered", "per": 1000000, "qualifier": "A minimum token-consumption rule applies when the input includes video; the threshold depends on resolution, aspect ratio, and output duration.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 4, "applies_when": [ "service_tier=default", "resolution=4k", "input_video=false" ], "denomination": "USD", "id": "online-4k-without-video-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 2.4, "applies_when": [ "service_tier=default", "resolution=4k", "input_video=true" ], "denomination": "USD", "id": "online-4k-with-video-input", "kind": "metered", "per": 1000000, "qualifier": "A minimum token-consumption rule applies when the input includes video; the threshold depends on resolution, aspect ratio, and output duration.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "seed-model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://seed.bytedance.com/en/seedance2_0" }, { "id": "seed-launch", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://seed.bytedance.com/blog/seedance-2-0-official-launch" }, { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "video-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1520757" }, { "id": "series-tutorial", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2291680" }, { "id": "prompt-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2222480" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1159177" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "series-tutorial", "model-list", "pricing" ], "value": "dreamina-seedance-2-0-fast-260128" } ], "capability_profiles": [ { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "text-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 496, "source_ids": [ "video-api" ], "unit": "pixel", "width": 864 }, { "aspect_ratio": "4:3", "height": 560, "source_ids": [ "video-api" ], "unit": "pixel", "width": 752 }, { "aspect_ratio": "1:1", "height": 640, "source_ids": [ "video-api" ], "unit": "pixel", "width": 640 }, { "aspect_ratio": "3:4", "height": 752, "source_ids": [ "video-api" ], "unit": "pixel", "width": 560 }, { "aspect_ratio": "9:16", "height": 864, "source_ids": [ "video-api" ], "unit": "pixel", "width": 496 }, { "aspect_ratio": "21:9", "height": 432, "source_ids": [ "video-api" ], "unit": "pixel", "width": 992 } ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1280 }, { "aspect_ratio": "4:3", "height": 834, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1112 }, { "aspect_ratio": "1:1", "height": 960, "source_ids": [ "video-api" ], "unit": "pixel", "width": 960 }, { "aspect_ratio": "3:4", "height": 1112, "source_ids": [ "video-api" ], "unit": "pixel", "width": 834 }, { "aspect_ratio": "9:16", "height": 1280, "source_ids": [ "video-api" ], "unit": "pixel", "width": 720 }, { "aspect_ratio": "21:9", "height": 630, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1470 } ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial", "prompt-guide" ], "task": "text_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-frame-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api", "release-notes" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial" ], "task": "image_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-last-frame-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api", "release-notes" ], "state": "supported" }, { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64", "cropped_to_start_image_ratio_when_ratios_differ=true" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "end_image", "source_ids": [ "video-api", "release-notes" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial" ], "task": "first_last_frame_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "omni-reference-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 9, "media_type": "image", "min_count": 0, "role": "image_reference", "source_ids": [ "video-api", "series-tutorial", "release-notes" ], "state": "supported" }, { "constraints": [ "duration_seconds>=2", "aggregate_duration_seconds<=15", "resolution_tiers=480p,720p,1080p,4k", "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "total_pixels>=409600", "total_pixels<=8295044", "size_megabytes<=200", "frame_rate_fps>=24", "frame_rate_fps<=60", "video_codecs=H.264/AVC,H.265/HEVC", "audio_codecs=AAC,MP3" ], "duration_unit": "second", "encodings": [ "url", "asset_id" ], "formats": [ "mp4", "mov" ], "max_count": 3, "max_duration": 15, "media_type": "video", "min_count": 0, "role": "video_reference", "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, { "constraints": [ "duration_seconds>=2", "aggregate_duration_seconds<=15", "size_megabytes<=15", "request_body_megabytes<=64", "audio_only_input=false" ], "duration_unit": "second", "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "wav", "mp3" ], "max_count": 3, "max_duration": 15, "media_type": "audio", "min_count": 0, "role": "audio_reference", "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial", "prompt-guide" ], "task": "omni_reference_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "English" }, { "name": "Spanish" }, { "name": "Indonesian" }, { "name": "Portuguese" }, { "name": "Japanese" } ], "listed_count": 5, "published_label": "English, Spanish, Indonesian, Portuguese, and Japanese", "scope": "prompt_input", "source_ids": [ "video-api" ], "state": "supported" }, "limitations": [ { "id": "direct-real-human-face-input", "source_ids": [ "video-api" ], "summary": "BytePlus states that Seedance 2.0 series models do not support directly uploaded reference images or videos containing real human faces; trusted generated outputs, preset digital characters, or authorized real-person assets are the documented alternatives." }, { "id": "generated-audio-mono", "source_ids": [ "video-api" ], "summary": "BytePlus states that generated videos with audio use mono output regardless of the input audio channel count." }, { "id": "precise-timing-instability", "source_ids": [ "prompt-guide" ], "summary": "BytePlus states that precise prompt timing such as 0–3 second segments is unstable and that forcing strict segment durations may cause abnormal generation results." }, { "id": "narration-end-noise", "source_ids": [ "prompt-guide" ], "summary": "BytePlus states that videos with narration are likely to contain abrupt clicks or cut-off noise at the end." } ], "model": { "aliases": [ "Seedance 2.0 fast" ], "id": "bytedance/dreamina-seedance-2-0-fast", "lab": "ByteDance", "modality": "video", "name": "Dreamina Seedance 2.0 Fast", "source_ids": [ "series-tutorial", "model-list", "release-notes" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 5.6, "applies_when": [ "service_tier=default", "resolution=480p", "input_video=false" ], "denomination": "USD", "id": "online-list-480p-without-video-input", "kind": "metered", "per": 1000000, "qualifier": "Original list rate. BytePlus states that a 25% time-limited discount applies from 2026-08-07 14:00 UTC+8 through 2026-09-07 14:00 UTC+8.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 3.3, "applies_when": [ "service_tier=default", "resolution=480p", "input_video=true" ], "denomination": "USD", "id": "online-list-480p-with-video-input", "kind": "metered", "per": 1000000, "qualifier": "Original list rate. BytePlus states that a 25% time-limited discount applies from 2026-08-07 14:00 UTC+8 through 2026-09-07 14:00 UTC+8. A minimum token-consumption rule also applies when the input includes video.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 5.6, "applies_when": [ "service_tier=default", "resolution=720p", "input_video=false" ], "denomination": "USD", "id": "online-list-720p-without-video-input", "kind": "metered", "per": 1000000, "qualifier": "Original list rate. BytePlus states that a 25% time-limited discount applies from 2026-08-07 14:00 UTC+8 through 2026-09-07 14:00 UTC+8.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 3.3, "applies_when": [ "service_tier=default", "resolution=720p", "input_video=true" ], "denomination": "USD", "id": "online-list-720p-with-video-input", "kind": "metered", "per": 1000000, "qualifier": "Original list rate. BytePlus states that a 25% time-limited discount applies from 2026-08-07 14:00 UTC+8 through 2026-09-07 14:00 UTC+8. A minimum token-consumption rule also applies when the input includes video.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "id": "current-discounted-token-rates", "qualifier": "BytePlus publishes the temporary discount as 25% off the list rate but does not separately state the discounted USD-per-million-token amounts.", "source_ids": [ "pricing" ], "state": "unknown" } ], "source_ids": [ "pricing" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "video-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1520757" }, { "id": "series-tutorial", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2291680" }, { "id": "prompt-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2222480" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1159177" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "series-tutorial", "model-list", "pricing" ], "value": "dreamina-seedance-2-0-mini-260615" } ], "capability_profiles": [ { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "text-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 496, "source_ids": [ "video-api" ], "unit": "pixel", "width": 864 }, { "aspect_ratio": "4:3", "height": 560, "source_ids": [ "video-api" ], "unit": "pixel", "width": 752 }, { "aspect_ratio": "1:1", "height": 640, "source_ids": [ "video-api" ], "unit": "pixel", "width": 640 }, { "aspect_ratio": "3:4", "height": 752, "source_ids": [ "video-api" ], "unit": "pixel", "width": 560 }, { "aspect_ratio": "9:16", "height": 864, "source_ids": [ "video-api" ], "unit": "pixel", "width": 496 }, { "aspect_ratio": "21:9", "height": 432, "source_ids": [ "video-api" ], "unit": "pixel", "width": 992 } ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1280 }, { "aspect_ratio": "4:3", "height": 834, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1112 }, { "aspect_ratio": "1:1", "height": 960, "source_ids": [ "video-api" ], "unit": "pixel", "width": 960 }, { "aspect_ratio": "3:4", "height": 1112, "source_ids": [ "video-api" ], "unit": "pixel", "width": 834 }, { "aspect_ratio": "9:16", "height": 1280, "source_ids": [ "video-api" ], "unit": "pixel", "width": 720 }, { "aspect_ratio": "21:9", "height": 630, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1470 } ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial", "prompt-guide" ], "task": "text_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-frame-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api", "release-notes" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial" ], "task": "image_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-last-frame-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api", "release-notes" ], "state": "supported" }, { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64", "cropped_to_start_image_ratio_when_ratios_differ=true" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "end_image", "source_ids": [ "video-api", "release-notes" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial" ], "task": "first_last_frame_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api", "series-tutorial" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 15, "min": 4, "mode": "range", "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "omni-reference-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 9, "media_type": "image", "min_count": 0, "role": "image_reference", "source_ids": [ "video-api", "series-tutorial", "release-notes" ], "state": "supported" }, { "constraints": [ "duration_seconds>=2", "aggregate_duration_seconds<=15", "resolution_tiers=480p,720p,1080p,4k", "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "total_pixels>=409600", "total_pixels<=8295044", "size_megabytes<=200", "frame_rate_fps>=24", "frame_rate_fps<=60", "video_codecs=H.264/AVC,H.265/HEVC", "audio_codecs=AAC,MP3" ], "duration_unit": "second", "encodings": [ "url", "asset_id" ], "formats": [ "mp4", "mov" ], "max_count": 3, "max_duration": 15, "media_type": "video", "min_count": 0, "role": "video_reference", "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" }, { "constraints": [ "duration_seconds>=2", "aggregate_duration_seconds<=15", "size_megabytes<=15", "request_body_megabytes<=64", "audio_only_input=false" ], "duration_unit": "second", "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "wav", "mp3" ], "max_count": 3, "max_duration": 15, "media_type": "audio", "min_count": 0, "role": "audio_reference", "source_ids": [ "video-api", "series-tutorial", "prompt-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "series-tutorial" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "series-tutorial" ] } ], "source_ids": [ "model-list", "video-api", "series-tutorial" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-list", "video-api", "series-tutorial", "prompt-guide" ], "task": "omni_reference_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "English" }, { "name": "Spanish" }, { "name": "Indonesian" }, { "name": "Portuguese" }, { "name": "Japanese" } ], "listed_count": 5, "published_label": "English, Spanish, Indonesian, Portuguese, and Japanese", "scope": "prompt_input", "source_ids": [ "video-api" ], "state": "supported" }, "limitations": [ { "id": "direct-real-human-face-input", "source_ids": [ "video-api" ], "summary": "BytePlus states that Seedance 2.0 series models do not support directly uploaded reference images or videos containing real human faces; trusted generated outputs, preset digital characters, or authorized real-person assets are the documented alternatives." }, { "id": "generated-audio-mono", "source_ids": [ "video-api" ], "summary": "BytePlus states that generated videos with audio use mono output regardless of the input audio channel count." }, { "id": "precise-timing-instability", "source_ids": [ "prompt-guide" ], "summary": "BytePlus states that precise prompt timing such as 0–3 second segments is unstable and that forcing strict segment durations may cause abnormal generation results." }, { "id": "narration-end-noise", "source_ids": [ "prompt-guide" ], "summary": "BytePlus states that videos with narration are likely to contain abrupt clicks or cut-off noise at the end." } ], "model": { "aliases": [ "Seedance 2.0 mini" ], "id": "bytedance/dreamina-seedance-2-0-mini", "lab": "ByteDance", "modality": "video", "name": "Dreamina Seedance 2.0 Mini", "source_ids": [ "series-tutorial", "model-list", "release-notes" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 3.5, "applies_when": [ "service_tier=default", "resolution=480p", "input_video=false" ], "denomination": "USD", "id": "online-list-480p-without-video-input", "kind": "metered", "per": 1000000, "qualifier": "Original list rate. BytePlus states that a 60% time-limited discount applies from 2026-08-07 14:00 UTC+8 through 2026-09-07 14:00 UTC+8.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 2.1, "applies_when": [ "service_tier=default", "resolution=480p", "input_video=true" ], "denomination": "USD", "id": "online-list-480p-with-video-input", "kind": "metered", "per": 1000000, "qualifier": "Original list rate. BytePlus states that a 60% time-limited discount applies from 2026-08-07 14:00 UTC+8 through 2026-09-07 14:00 UTC+8. A minimum token-consumption rule also applies when the input includes video.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 3.5, "applies_when": [ "service_tier=default", "resolution=720p", "input_video=false" ], "denomination": "USD", "id": "online-list-720p-without-video-input", "kind": "metered", "per": 1000000, "qualifier": "Original list rate. BytePlus states that a 60% time-limited discount applies from 2026-08-07 14:00 UTC+8 through 2026-09-07 14:00 UTC+8.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 2.1, "applies_when": [ "service_tier=default", "resolution=720p", "input_video=true" ], "denomination": "USD", "id": "online-list-720p-with-video-input", "kind": "metered", "per": 1000000, "qualifier": "Original list rate. BytePlus states that a 60% time-limited discount applies from 2026-08-07 14:00 UTC+8 through 2026-09-07 14:00 UTC+8. A minimum token-consumption rule also applies when the input includes video.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "id": "current-discounted-token-rates", "qualifier": "BytePlus publishes the temporary discount as 60% off the list rate but does not separately state the discounted USD-per-million-token amounts.", "source_ids": [ "pricing" ], "state": "unknown" } ], "source_ids": [ "pricing" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "video-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1520757" }, { "id": "series-tutorial", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2291680" }, { "id": "prompt-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2222480" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1159177" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "audio-api" ], "value": "seed-audio-1.0" } ], "capability_profiles": [ { "api_mode": "references omitted", "audio_formats": [ { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] } ], "controls": [ { "default": "wav", "mode": "exact_set", "name": "output_format", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "wav", "mp3", "pcm", "ogg_opus" ] }, { "mode": "exact_set", "name": "sample_rate", "source_ids": [ "audio-api" ], "state": "supported", "unit": "hertz", "values": [ "8000", "16000", "24000", "32000", "44100", "48000" ] }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "pitch_step" }, { "default": 0, "max": 100, "min": -50, "mode": "range", "name": "speech_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "rate_adjustment" }, { "default": 0, "max": 100, "min": -50, "mode": "range", "name": "loudness_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "volume_adjustment" }, { "default": "false", "mode": "exact_set", "name": "enable_subtitle", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "aigc_watermark", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "implicit_metadata_watermark", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "wav", "endpoint": "POST /api/v3/tts/create", "formats": [ "wav", "mp3", "pcm", "ogg_opus" ], "id": "base64-response", "source_ids": [ "audio-api" ], "state": "supported", "transport": "base64_inline" }, { "default_format": "wav", "endpoint": "POST /api/v3/tts/create", "formats": [ "wav", "mp3", "pcm", "ogg_opus" ], "id": "temporary-url", "source_ids": [ "audio-api" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "audio-api" ], "state": "unknown" }, "endpoint": "POST https://voice.ap-southeast-1.bytepluses.com/api/v3/tts/create", "frame_rate": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "id": "text-to-audio", "native_audio": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "size": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "source_ids": [ "audio-api" ], "task": "text_to_audio", "text_input": { "max": 3000, "source_ids": [ "audio-api" ], "state": "supported", "unit": "character" }, "timing": { "delivery_profile_ids": [ "base64-response", "temporary-url" ], "endpoints": [ "POST /api/v3/tts/create" ], "granularity": "word", "metadata": [ "subtitle.sentences.start_time", "subtitle.sentences.end_time", "subtitle.words.start_time", "subtitle.words.end_time" ], "source_ids": [ "audio-api" ], "state": "supported" } }, { "api_mode": "references contains audio_url or audio_data", "audio_formats": [ { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] } ], "controls": [ { "default": "wav", "mode": "exact_set", "name": "output_format", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "wav", "mp3", "pcm", "ogg_opus" ] }, { "mode": "exact_set", "name": "sample_rate", "source_ids": [ "audio-api" ], "state": "supported", "unit": "hertz", "values": [ "8000", "16000", "24000", "32000", "44100", "48000" ] }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "pitch_step" }, { "default": 0, "max": 100, "min": -50, "mode": "range", "name": "speech_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "rate_adjustment" }, { "default": 0, "max": 100, "min": -50, "mode": "range", "name": "loudness_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "volume_adjustment" }, { "default": "false", "mode": "exact_set", "name": "enable_subtitle", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "aigc_watermark", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "implicit_metadata_watermark", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "wav", "endpoint": "POST /api/v3/tts/create", "formats": [ "wav", "mp3", "pcm", "ogg_opus" ], "id": "base64-response", "source_ids": [ "audio-api" ], "state": "supported", "transport": "base64_inline" }, { "default_format": "wav", "endpoint": "POST /api/v3/tts/create", "formats": [ "wav", "mp3", "pcm", "ogg_opus" ], "id": "temporary-url", "source_ids": [ "audio-api" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "audio-api" ], "state": "unknown" }, "endpoint": "POST https://voice.ap-southeast-1.bytepluses.com/api/v3/tts/create", "frame_rate": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "id": "reference-audio-to-audio", "native_audio": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "size_bytes<=10000000", "one_source_selector_per_reference", "cannot_mix_with_image_reference" ], "duration_unit": "second", "encodings": [ "url", "base64_data" ], "formats": [ "wav", "mp3", "pcm", "ogg_opus" ], "max_count": 3, "max_duration": 30, "media_type": "audio", "min_count": 1, "role": "audio_reference", "source_ids": [ "audio-api" ], "state": "supported" } ], "size": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "source_ids": [ "audio-api" ], "task": "reference_audio_to_audio", "text_input": { "max": 3000, "source_ids": [ "audio-api" ], "state": "supported", "unit": "character" }, "timing": { "delivery_profile_ids": [ "base64-response", "temporary-url" ], "endpoints": [ "POST /api/v3/tts/create" ], "granularity": "word", "metadata": [ "subtitle.sentences.start_time", "subtitle.sentences.end_time", "subtitle.words.start_time", "subtitle.words.end_time" ], "source_ids": [ "audio-api" ], "state": "supported" } }, { "api_mode": "references contains speaker", "audio_formats": [ { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] } ], "controls": [ { "default": "wav", "mode": "exact_set", "name": "output_format", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "wav", "mp3", "pcm", "ogg_opus" ] }, { "mode": "exact_set", "name": "sample_rate", "source_ids": [ "audio-api" ], "state": "supported", "unit": "hertz", "values": [ "8000", "16000", "24000", "32000", "44100", "48000" ] }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "pitch_step" }, { "default": 0, "max": 100, "min": -50, "mode": "range", "name": "speech_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "rate_adjustment" }, { "default": 0, "max": 100, "min": -50, "mode": "range", "name": "loudness_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "volume_adjustment" }, { "default": "false", "mode": "exact_set", "name": "enable_subtitle", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "aigc_watermark", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "implicit_metadata_watermark", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "wav", "endpoint": "POST /api/v3/tts/create", "formats": [ "wav", "mp3", "pcm", "ogg_opus" ], "id": "base64-response", "source_ids": [ "audio-api" ], "state": "supported", "transport": "base64_inline" }, { "default_format": "wav", "endpoint": "POST /api/v3/tts/create", "formats": [ "wav", "mp3", "pcm", "ogg_opus" ], "id": "temporary-url", "source_ids": [ "audio-api" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "audio-api" ], "state": "unknown" }, "endpoint": "POST https://voice.ap-southeast-1.bytepluses.com/api/v3/tts/create", "frame_rate": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "id": "speaker-conditioned-audio", "native_audio": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "tts_2_0_voice_or_cloned_voice", "cannot_mix_with_image_reference", "one_source_selector_per_reference" ], "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "audio-api" ], "state": "supported" } ], "size": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "source_ids": [ "audio-api" ], "task": "speaker_conditioned_audio", "text_input": { "max": 3000, "source_ids": [ "audio-api" ], "state": "supported", "unit": "character" }, "timing": { "delivery_profile_ids": [ "base64-response", "temporary-url" ], "endpoints": [ "POST /api/v3/tts/create" ], "granularity": "word", "metadata": [ "subtitle.sentences.start_time", "subtitle.sentences.end_time", "subtitle.words.start_time", "subtitle.words.end_time" ], "source_ids": [ "audio-api" ], "state": "supported" } }, { "api_mode": "references contains image_url or image_data", "audio_formats": [ { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] }, { "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 24000, 32000, 44100, 48000 ], "source_ids": [ "audio-api" ] } ], "controls": [ { "default": "wav", "mode": "exact_set", "name": "output_format", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "wav", "mp3", "pcm", "ogg_opus" ] }, { "mode": "exact_set", "name": "sample_rate", "source_ids": [ "audio-api" ], "state": "supported", "unit": "hertz", "values": [ "8000", "16000", "24000", "32000", "44100", "48000" ] }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "pitch_step" }, { "default": 0, "max": 100, "min": -50, "mode": "range", "name": "speech_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "rate_adjustment" }, { "default": 0, "max": 100, "min": -50, "mode": "range", "name": "loudness_rate", "source_ids": [ "audio-api" ], "state": "supported", "step": 1, "unit": "volume_adjustment" }, { "default": "false", "mode": "exact_set", "name": "enable_subtitle", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "aigc_watermark", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "implicit_metadata_watermark", "source_ids": [ "audio-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "wav", "endpoint": "POST /api/v3/tts/create", "formats": [ "wav", "mp3", "pcm", "ogg_opus" ], "id": "base64-response", "source_ids": [ "audio-api" ], "state": "supported", "transport": "base64_inline" }, { "default_format": "wav", "endpoint": "POST /api/v3/tts/create", "formats": [ "wav", "mp3", "pcm", "ogg_opus" ], "id": "temporary-url", "source_ids": [ "audio-api" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "audio-api" ], "state": "unknown" }, "endpoint": "POST https://voice.ap-southeast-1.bytepluses.com/api/v3/tts/create", "frame_rate": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "id": "image-to-audio", "native_audio": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "size_bytes<=10000000", "one_source_selector_per_reference", "cannot_mix_with_audio_reference" ], "encodings": [ "url", "base64_data" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "audio-api" ], "state": "supported" } ], "size": { "source_ids": [ "audio-api" ], "state": "not_applicable" }, "source_ids": [ "audio-api" ], "task": "image_to_audio", "text_input": { "max": 3000, "source_ids": [ "audio-api" ], "state": "supported", "unit": "character" }, "timing": { "delivery_profile_ids": [ "base64-response", "temporary-url" ], "endpoints": [ "POST /api/v3/tts/create" ], "granularity": "word", "metadata": [ "subtitle.sentences.start_time", "subtitle.sentences.end_time", "subtitle.words.start_time", "subtitle.words.end_time" ], "source_ids": [ "audio-api" ], "state": "supported" } } ], "conflicts": [ { "handling": "Record only the explicit valid-value set and leave per-format defaults unmodeled until BytePlus resolves the contradiction.", "path": "capability_profiles.audio_formats.sample_rates", "source_ids": [ "audio-api" ], "summary": "The API reference lists valid sample rates as 8000, 16000, 24000, 32000, 44100, and 48000 Hz, but separately states a 40000 Hz default for WAV and PCM, which is absent from that valid-value list." } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "English" }, { "name": "Chinese" }, { "name": "Japanese" }, { "name": "Korean" }, { "name": "Mexican Spanish" }, { "name": "Indonesian" }, { "name": "German" }, { "name": "Brazilian Portuguese" }, { "name": "French" }, { "name": "Thai" }, { "name": "Vietnamese" }, { "name": "Malay" }, { "name": "Filipino" }, { "name": "Italian" }, { "name": "Russian" }, { "name": "Dutch" }, { "name": "Polish" }, { "name": "Turkish" }, { "name": "Swedish" }, { "name": "Castilian Spanish" } ], "listed_count": 20, "published_label": "English, Chinese, Japanese, Korean, Mexican Spanish, Indonesian, German, Brazilian Portuguese, French, Thai, Vietnamese, Malay, Filipino, Italian, Russian, Dutch, Polish, Turkish, Swedish, and Castilian Spanish", "scope": "speech_output", "source_ids": [ "audio-api" ], "state": "supported" }, "limitations": [ { "id": "maximum-output-duration", "source_ids": [ "audio-api" ], "summary": "BytePlus states that generated audio is limited to 120 seconds, but does not publish a complete minimum-to-maximum duration range; original_duration is capped at 120 seconds and is the billing duration." }, { "id": "non-streaming-api", "source_ids": [ "audio-api" ], "summary": "BytePlus describes the HTTP Audio 1.0 endpoint as non-streaming." }, { "id": "temporary-url-expiry", "source_ids": [ "audio-api" ], "summary": "Returned audio URLs are valid for two hours." } ], "model": { "id": "bytedance/seed-audio-1-0", "lab": "ByteDance", "modality": "audio", "name": "Seed Audio 1.0", "source_ids": [ "lab-page", "audio-api", "pricing" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 14, "denomination": "point", "id": "timbre-audio-generation", "kind": "metered", "per": 1, "qualifier": "BytePlus Dramagic publishes 14 points per second and labels this as equivalent to USD 0.14 per second; billing uses the model's original_duration before speed adjustment or post-processing.", "source_ids": [ "audio-api", "pricing" ], "state": "known", "unit": "original_audio_second" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "lab-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://seed.bytedance.com/en/seedaudio1_0" }, { "id": "audio-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/byteplusvoice/seedaudio-01?lang=en" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/Dramagic/PlansPackages" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "model-list", "video-api", "pricing" ], "value": "seedance-1-0-pro-250528" } ], "capability_profiles": [ { "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ] }, { "max": 289, "min": 29, "mode": "range", "name": "frames", "source_ids": [ "video-api" ], "state": "supported", "step": 4, "unit": "frame" }, { "default": -1, "max": 2147483647, "min": -1, "mode": "range", "name": "seed", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "integer" }, { "default": "false", "mode": "exact_set", "name": "camera_fixed", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 12, "min": 2, "mode": "range", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-page", "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "text-to-video", "native_audio": { "source_ids": [ "model-page", "video-api" ], "state": "unsupported" }, "size": { "default": "1080p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 480, "source_ids": [ "video-api" ], "unit": "pixel", "width": 864 }, { "aspect_ratio": "4:3", "height": 544, "source_ids": [ "video-api" ], "unit": "pixel", "width": 736 }, { "aspect_ratio": "1:1", "height": 640, "source_ids": [ "video-api" ], "unit": "pixel", "width": 640 }, { "aspect_ratio": "3:4", "height": 736, "source_ids": [ "video-api" ], "unit": "pixel", "width": 544 }, { "aspect_ratio": "9:16", "height": 864, "source_ids": [ "video-api" ], "unit": "pixel", "width": 480 }, { "aspect_ratio": "21:9", "height": 416, "source_ids": [ "video-api" ], "unit": "pixel", "width": 960 } ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 704, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1248 }, { "aspect_ratio": "4:3", "height": 832, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1120 }, { "aspect_ratio": "1:1", "height": 960, "source_ids": [ "video-api" ], "unit": "pixel", "width": 960 }, { "aspect_ratio": "3:4", "height": 1120, "source_ids": [ "video-api" ], "unit": "pixel", "width": 832 }, { "aspect_ratio": "9:16", "height": 1248, "source_ids": [ "video-api" ], "unit": "pixel", "width": 704 }, { "aspect_ratio": "21:9", "height": 640, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1504 } ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "4:3", "height": 1248, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1664 }, { "aspect_ratio": "1:1", "height": 1440, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1440 }, { "aspect_ratio": "3:4", "height": 1664, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1248 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 928, "source_ids": [ "video-api" ], "unit": "pixel", "width": 2176 } ], "id": "1080p", "label": "1080p", "source_ids": [ "video-api", "prompt-guide" ] } ], "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "model-list", "video-api", "prompt-guide" ], "task": "text_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "max": 289, "min": 29, "mode": "range", "name": "frames", "source_ids": [ "video-api" ], "state": "supported", "step": 4, "unit": "frame" }, { "default": -1, "max": 2147483647, "min": -1, "mode": "range", "name": "seed", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "integer" }, { "name": "camera_fixed", "source_ids": [ "video-api" ], "state": "unsupported" }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 12, "min": 2, "mode": "range", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-page", "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-frame-to-video", "native_audio": { "source_ids": [ "model-page", "video-api" ], "state": "unsupported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api" ], "state": "supported" } ], "size": { "default": "1080p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "1080p", "label": "1080p", "source_ids": [ "video-api", "prompt-guide" ] } ], "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "model-list", "video-api", "prompt-guide" ], "task": "image_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "max": 289, "min": 29, "mode": "range", "name": "frames", "source_ids": [ "video-api" ], "state": "supported", "step": 4, "unit": "frame" }, { "default": -1, "max": 2147483647, "min": -1, "mode": "range", "name": "seed", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "integer" }, { "name": "camera_fixed", "source_ids": [ "video-api" ], "state": "unsupported" }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 12, "min": 2, "mode": "range", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-page", "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-last-frame-to-video", "native_audio": { "source_ids": [ "model-page", "video-api" ], "state": "unsupported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api" ], "state": "supported" }, { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64", "cropped_to_start_image_ratio_when_ratios_differ=true" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "end_image", "source_ids": [ "video-api" ], "state": "supported" } ], "size": { "default": "1080p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "1080p", "label": "1080p", "source_ids": [ "video-api", "prompt-guide" ] } ], "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "model-list", "video-api", "prompt-guide" ], "task": "first_last_frame_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "Chinese" }, { "name": "English" } ], "listed_count": 2, "published_label": "Chinese and English", "scope": "prompt_input", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported" }, "model": { "id": "bytedance/seedance-1-0-pro", "lab": "ByteDance", "modality": "video", "name": "Seedance 1.0 Pro", "source_ids": [ "model-page", "model-list", "prompt-guide" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 2.5, "applies_when": [ "service_tier=default" ], "denomination": "USD", "id": "online", "kind": "metered", "per": 1000000, "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 1.25, "applies_when": [ "service_tier=flex" ], "denomination": "USD", "id": "offline", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" } ], "source_ids": [ "model-page", "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1587798" }, { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "video-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1520757" }, { "id": "prompt-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1631633" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "model-list", "video-api", "pricing" ], "value": "seedance-1-0-pro-fast-251015" } ], "capability_profiles": [ { "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ] }, { "max": 289, "min": 29, "mode": "range", "name": "frames", "source_ids": [ "video-api" ], "state": "supported", "step": 4, "unit": "frame" }, { "default": -1, "max": 2147483647, "min": -1, "mode": "range", "name": "seed", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "integer" }, { "default": "false", "mode": "exact_set", "name": "camera_fixed", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 12, "min": 2, "mode": "range", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-page", "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "text-to-video", "native_audio": { "source_ids": [ "model-page", "video-api" ], "state": "unsupported" }, "size": { "default": "1080p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 480, "source_ids": [ "video-api" ], "unit": "pixel", "width": 864 }, { "aspect_ratio": "4:3", "height": 544, "source_ids": [ "video-api" ], "unit": "pixel", "width": 736 }, { "aspect_ratio": "1:1", "height": 640, "source_ids": [ "video-api" ], "unit": "pixel", "width": 640 }, { "aspect_ratio": "3:4", "height": 736, "source_ids": [ "video-api" ], "unit": "pixel", "width": 544 }, { "aspect_ratio": "9:16", "height": 864, "source_ids": [ "video-api" ], "unit": "pixel", "width": 480 }, { "aspect_ratio": "21:9", "height": 416, "source_ids": [ "video-api" ], "unit": "pixel", "width": 960 } ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 704, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1248 }, { "aspect_ratio": "4:3", "height": 832, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1120 }, { "aspect_ratio": "1:1", "height": 960, "source_ids": [ "video-api" ], "unit": "pixel", "width": 960 }, { "aspect_ratio": "3:4", "height": 1120, "source_ids": [ "video-api" ], "unit": "pixel", "width": 832 }, { "aspect_ratio": "9:16", "height": 1248, "source_ids": [ "video-api" ], "unit": "pixel", "width": 704 }, { "aspect_ratio": "21:9", "height": 640, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1504 } ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 1088, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "4:3", "height": 1248, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1664 }, { "aspect_ratio": "1:1", "height": 1440, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1440 }, { "aspect_ratio": "3:4", "height": 1664, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1248 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1088 }, { "aspect_ratio": "21:9", "height": 928, "source_ids": [ "video-api" ], "unit": "pixel", "width": 2176 } ], "id": "1080p", "label": "1080p", "source_ids": [ "video-api", "prompt-guide" ] } ], "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "model-list", "video-api", "prompt-guide" ], "task": "text_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "max": 289, "min": 29, "mode": "range", "name": "frames", "source_ids": [ "video-api" ], "state": "supported", "step": 4, "unit": "frame" }, { "default": -1, "max": 2147483647, "min": -1, "mode": "range", "name": "seed", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "integer" }, { "name": "camera_fixed", "source_ids": [ "video-api" ], "state": "unsupported" }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 12, "min": 2, "mode": "range", "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-page", "model-list" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-frame-to-video", "native_audio": { "source_ids": [ "model-page", "video-api" ], "state": "unsupported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.4", "width_to_height_ratio<=2.5", "width_px>=300", "width_px<=6000", "height_px>=300", "height_px<=6000", "size_megabytes<30", "request_body_megabytes<=64" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api" ], "state": "supported" } ], "size": { "default": "1080p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "source_ids": [ "video-api", "prompt-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "1080p", "label": "1080p", "source_ids": [ "video-api", "prompt-guide" ] } ], "source_ids": [ "model-page", "model-list", "video-api" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "model-list", "video-api", "prompt-guide" ], "task": "image_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "Chinese" }, { "name": "English" } ], "listed_count": 2, "published_label": "Chinese and English", "scope": "prompt_input", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported" }, "model": { "id": "bytedance/seedance-1-0-pro-fast", "lab": "ByteDance", "modality": "video", "name": "Seedance 1.0 Pro Fast", "source_ids": [ "model-page", "model-list", "prompt-guide" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 1, "applies_when": [ "service_tier=default" ], "denomination": "USD", "id": "online", "kind": "metered", "per": 1000000, "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 0.5, "applies_when": [ "service_tier=flex" ], "denomination": "USD", "id": "offline", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" } ], "source_ids": [ "model-page", "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1901652" }, { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "video-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1520757" }, { "id": "prompt-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1631633" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "video-api", "video-guide", "model-list", "pricing" ], "value": "seedance-1-5-pro-251215" } ], "capability_profiles": [ { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "video-guide" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "video" }, { "default": -1, "max": 4294967295, "min": -1, "mode": "range", "name": "seed", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "integer" }, { "default": "false", "mode": "exact_set", "name": "camera_fixed", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api", "prompt-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "draft", "source_ids": [ "video-api", "video-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "video-guide" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 12, "min": 4, "mode": "range", "source_ids": [ "video-api", "video-guide" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list", "video-api" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "text-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "video-guide", "prompt-guide" ], "state": "supported" }, "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 496, "source_ids": [ "video-api" ], "unit": "pixel", "width": 864 }, { "aspect_ratio": "4:3", "height": 560, "source_ids": [ "video-api" ], "unit": "pixel", "width": 752 }, { "aspect_ratio": "1:1", "height": 640, "source_ids": [ "video-api" ], "unit": "pixel", "width": 640 }, { "aspect_ratio": "3:4", "height": 752, "source_ids": [ "video-api" ], "unit": "pixel", "width": 560 }, { "aspect_ratio": "9:16", "height": 864, "source_ids": [ "video-api" ], "unit": "pixel", "width": 496 }, { "aspect_ratio": "21:9", "height": 432, "source_ids": [ "video-api" ], "unit": "pixel", "width": 992 } ], "id": "480p", "label": "480p", "render_modes": [ "normal", "draft" ], "source_ids": [ "video-api", "video-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1280 }, { "aspect_ratio": "4:3", "height": 834, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1112 }, { "aspect_ratio": "1:1", "height": 960, "source_ids": [ "video-api" ], "unit": "pixel", "width": 960 }, { "aspect_ratio": "3:4", "height": 1112, "source_ids": [ "video-api" ], "unit": "pixel", "width": 834 }, { "aspect_ratio": "9:16", "height": 1280, "source_ids": [ "video-api" ], "unit": "pixel", "width": 720 }, { "aspect_ratio": "21:9", "height": 630, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1470 } ], "id": "720p", "label": "720p", "render_modes": [ "normal" ], "source_ids": [ "video-api", "video-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 1080, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "4:3", "height": 1248, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1664 }, { "aspect_ratio": "1:1", "height": 1440, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1440 }, { "aspect_ratio": "3:4", "height": 1664, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1248 }, { "aspect_ratio": "9:16", "height": 1920, "source_ids": [ "video-api" ], "unit": "pixel", "width": 1080 }, { "aspect_ratio": "21:9", "height": 946, "source_ids": [ "video-api" ], "unit": "pixel", "width": 2206 } ], "id": "1080p", "label": "1080p", "render_modes": [ "normal" ], "source_ids": [ "video-api", "video-guide" ] } ], "source_ids": [ "model-list", "video-api", "video-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "video-api", "video-guide", "prompt-guide" ], "task": "text_to_video", "text_input": { "source_ids": [ "video-api", "prompt-guide" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "video-guide" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "video" }, { "default": -1, "max": 4294967295, "min": -1, "mode": "range", "name": "seed", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "integer" }, { "default": "false", "mode": "exact_set", "name": "camera_fixed", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "draft", "source_ids": [ "video-api", "video-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "video-guide" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 12, "min": 4, "mode": "range", "source_ids": [ "video-api", "video-guide" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list", "video-api" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-frame-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "video-guide", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>0.4", "width_to_height_ratio<2.5", "width_px>300", "width_px<6000", "height_px>300", "height_px<6000", "size_bytes<30000000", "request_body_bytes<=64000000" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "render_modes": [ "normal", "draft" ], "source_ids": [ "video-api", "video-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "render_modes": [ "normal" ], "source_ids": [ "video-api", "video-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "1080p", "label": "1080p", "render_modes": [ "normal" ], "source_ids": [ "video-api", "video-guide" ] } ], "source_ids": [ "model-list", "video-api", "video-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "video-api", "video-guide" ], "task": "image_to_video", "text_input": { "source_ids": [ "video-api" ], "state": "unknown" } }, { "controls": [ { "default": "adaptive", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "video-api", "video-guide" ], "state": "supported", "values": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9", "adaptive" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "video" }, { "default": -1, "max": 4294967295, "min": -1, "mode": "range", "name": "seed", "source_ids": [ "video-api" ], "state": "supported", "step": 1, "unit": "integer" }, { "default": "false", "mode": "exact_set", "name": "camera_fixed", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "watermark", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "draft", "source_ids": [ "video-api", "video-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "return_last_frame", "source_ids": [ "video-api" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "mp4-task-result", "source_ids": [ "model-list", "video-api", "video-guide" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "automatic": true, "max": 12, "min": 4, "mode": "range", "source_ids": [ "video-api", "video-guide" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /api/v3/contents/generations/tasks", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-list", "video-api" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "first-last-frame-to-video", "native_audio": { "default": true, "source_ids": [ "video-api", "video-guide", "prompt-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>0.4", "width_to_height_ratio<2.5", "width_px>300", "width_px<6000", "height_px>300", "height_px<6000", "size_bytes<30000000", "request_body_bytes<=64000000" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "video-api" ], "state": "supported" }, { "constraints": [ "width_to_height_ratio>0.4", "width_to_height_ratio<2.5", "width_px>300", "width_px<6000", "height_px>300", "height_px<6000", "size_bytes<30000000", "request_body_bytes<=64000000", "cropped_to_start_image_ratio_when_ratios_differ" ], "encodings": [ "url", "base64_data_url", "asset_id" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "end_image", "source_ids": [ "video-api" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "480p", "label": "480p", "render_modes": [ "normal", "draft" ], "source_ids": [ "video-api", "video-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "720p", "label": "720p", "render_modes": [ "normal" ], "source_ids": [ "video-api", "video-guide" ] }, { "aspect_ratios": [ "16:9", "4:3", "1:1", "3:4", "9:16", "21:9" ], "id": "1080p", "label": "1080p", "render_modes": [ "normal" ], "source_ids": [ "video-api", "video-guide" ] } ], "source_ids": [ "model-list", "video-api", "video-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "release-notes", "video-api", "video-guide" ], "task": "first_last_frame_to_video", "text_input": { "source_ids": [ "video-api" ], "state": "unknown" } } ], "conflicts": [ { "handling": "Record the identifier consistently used by the serving API and pricing table; retain the prompt-guide spelling as unresolved official-source drift rather than claiming it is an alias.", "path": "api_identifiers", "source_ids": [ "video-api", "video-guide", "prompt-guide", "model-list", "pricing" ], "summary": "The current API reference, tutorial, model list, and pricing table use seedance-1-5-pro-251215, while the dedicated prompt guide's examples use doubao-seedance-1-5-pro-251215." } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "Mandarin Chinese" }, { "name": "Cantonese" }, { "name": "Shaanxi dialect" }, { "name": "Sichuan dialect" }, { "name": "English" }, { "name": "Japanese" }, { "name": "Korean" }, { "name": "Spanish" }, { "name": "Indonesian" } ], "list_completeness": "non_exhaustive", "listed_count": 9, "published_label": "Mandarin and major Chinese dialects, plus English, Japanese, Korean, Spanish, and Indonesian", "scope": "native_audio", "source_ids": [ "prompt-guide" ], "state": "supported" }, "limitations": [ { "id": "generated-audio-mono", "source_ids": [ "video-api" ], "summary": "BytePlus states that generated videos with audio use mono output regardless of the input audio channel count." }, { "id": "draft-mode-restrictions", "source_ids": [ "video-api", "video-guide" ], "summary": "Draft mode is limited to 480p and cannot be combined with last-frame return or offline inference." } ], "model": { "id": "bytedance/seedance-1-5-pro", "lab": "ByteDance", "modality": "video", "name": "Seedance 1.5 Pro", "source_ids": [ "model-list", "release-notes", "video-api", "prompt-guide" ], "status": "available" }, "pricing": { "charges": [ { "amount": 2.4, "applies_when": [ "service_tier=default", "generate_audio=true" ], "denomination": "USD", "id": "online-with-audio", "kind": "metered", "per": 1000000, "qualifier": "Draft mode uses the same token unit price but an estimated 0.6 token-consumption conversion factor.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 1.2, "applies_when": [ "service_tier=default", "generate_audio=false" ], "denomination": "USD", "id": "online-silent", "kind": "metered", "per": 1000000, "qualifier": "Draft mode uses the same token unit price but an estimated 0.7 token-consumption conversion factor.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 1.2, "applies_when": [ "service_tier=flex", "generate_audio=true", "draft=false" ], "denomination": "USD", "id": "offline-with-audio", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 0.6, "applies_when": [ "service_tier=flex", "generate_audio=false", "draft=false" ], "denomination": "USD", "id": "offline-silent", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "video-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1520757" }, { "id": "video-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2298881" }, { "id": "prompt-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2168087" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2172655" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "pricing" ], "value": "dreamina-seedance-2-5-260628" } ], "capability_profiles": [ { "id": "text-to-video", "source_ids": [ "model-page" ], "task": "text_to_video" } ], "conflicts": [ { "handling": "Keep the record indexed and do not reuse Seedance 2.0 duration, resolution, reference-input, audio, or control values until BytePlus publishes a Seedance 2.5 serving contract.", "path": "capability_profiles", "source_ids": [ "model-page", "pricing", "video-api", "video-guide" ], "summary": "ByteDance's model page publishes Seedance 2.5 and the ModelArk pricing table publishes its model ID and token rates, but the current ModelArk Video Generation API reference and tutorial do not include Seedance 2.5 in their supported-model parameter tables." } ], "documentation_state": "indexed", "model": { "id": "bytedance/seedance-2-5", "lab": "ByteDance", "modality": "video", "name": "Seedance 2.5", "source_ids": [ "model-page", "pricing" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 10.7, "applies_when": [ "output_resolution=480p_or_720p", "input_video=false", "service_tier=default" ], "denomination": "USD", "id": "online-without-video-input", "kind": "metered", "per": 1000000, "qualifier": "The current ModelArk pricing table publishes this online-inference rate and marks offline inference as not supported.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" }, { "amount": 6.4, "applies_when": [ "output_resolution=480p_or_720p", "input_video=true", "service_tier=default" ], "denomination": "USD", "id": "online-with-video-input", "kind": "metered", "per": 1000000, "qualifier": "The current ModelArk pricing table publishes this online-inference rate and marks offline inference as not supported.", "source_ids": [ "pricing" ], "state": "known", "unit": "video_generation_token" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://seed.bytedance.com/en/seedance2_5" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" }, { "id": "video-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1520757" }, { "id": "video-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2298881" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "model-list", "image-api", "image-guide", "pricing" ], "value": "seedream-4-0-250828" } ], "capability_profiles": [ { "api_mode": "sequential_image_generation=disabled", "controls": [ { "mode": "exact_set", "name": "size_preset", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "values": [ "1K", "2K", "4K" ] }, { "default": "true", "mode": "exact_set", "name": "watermark", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "name": "guidance_scale", "source_ids": [ "image-api" ], "state": "unsupported" }, { "default": "standard", "mode": "exact_set", "name": "prompt_optimization_mode", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "standard", "fast" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "url", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "base64-json", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" }, { "default_format": "jpeg", "endpoint": "POST /api/v3/images/generations", "formats": [ "jpeg" ], "id": "server-sent-events", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "transport": "server_sent_events" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "size": { "default": "2048x2048", "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "model-page", "image-api" ], "unit": "pixel", "width": 1280 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "model-page", "image-api" ], "unit": "pixel", "width": 4096 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 16777216, "min_total_pixels": 921600, "mode": "range", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "model-page", "image-api", "image-guide", "prompt-guide" ], "task": "text_to_image", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } }, { "api_mode": "sequential_image_generation=disabled", "controls": [ { "mode": "exact_set", "name": "size_preset", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "values": [ "1K", "2K", "4K" ] }, { "default": "true", "mode": "exact_set", "name": "watermark", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "name": "guidance_scale", "source_ids": [ "image-api" ], "state": "unsupported" }, { "default": "standard", "mode": "exact_set", "name": "prompt_optimization_mode", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "standard", "fast" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "url", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "base64-json", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" }, { "default_format": "jpeg", "endpoint": "POST /api/v3/images/generations", "formats": [ "jpeg" ], "id": "server-sent-events", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "transport": "server_sent_events" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>=0.0625", "width_to_height_ratio<=16", "width_px>14", "height_px>14", "size_bytes<=30000000", "total_pixels<=36000000" ], "encodings": [ "url", "base64_data_url" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 14, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "image-api", "image-guide" ], "state": "supported" } ], "size": { "default": "2048x2048", "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "model-page", "image-api" ], "unit": "pixel", "width": 1280 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "model-page", "image-api" ], "unit": "pixel", "width": 4096 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 16777216, "min_total_pixels": 921600, "mode": "range", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "model-page", "image-api", "image-guide", "prompt-guide" ], "task": "image_edit", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } }, { "api_mode": "sequential_image_generation=auto", "controls": [ { "default": 15, "max": 15, "min": 1, "mode": "range", "name": "maximum_output_images", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "step": 1, "unit": "image" }, { "mode": "exact_set", "name": "size_preset", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "values": [ "1K", "2K", "4K" ] }, { "default": "true", "mode": "exact_set", "name": "watermark", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "standard", "mode": "exact_set", "name": "prompt_optimization_mode", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "standard", "fast" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "buffered-url", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "base64-json", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" }, { "default_format": "jpeg", "endpoint": "POST /api/v3/images/generations", "formats": [ "jpeg" ], "id": "server-sent-events", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "transport": "server_sent_events" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "batch-image-generation", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "input_image_count+generated_image_count<=15", "width_to_height_ratio>=0.0625", "width_to_height_ratio<=16", "width_px>14", "height_px>14", "size_bytes<=30000000", "total_pixels<=36000000" ], "encodings": [ "url", "base64_data_url" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 14, "media_type": "image", "min_count": 0, "role": "image_reference", "source_ids": [ "image-api", "image-guide" ], "state": "supported" } ], "size": { "default": "2048x2048", "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "model-page", "image-api" ], "unit": "pixel", "width": 1280 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "model-page", "image-api" ], "unit": "pixel", "width": 4096 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 16777216, "min_total_pixels": 921600, "mode": "range", "source_ids": [ "model-page", "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "model-page", "image-api", "image-guide", "prompt-guide" ], "task": "batch_image_generation", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } } ], "conflicts": [ { "handling": "Record the current serving API limit of 14; retain the older model-card limit as unresolved first-party documentation drift.", "path": "capability_profiles.image-edit.reference_inputs.max_count", "source_ids": [ "model-page", "image-api", "image-guide" ], "summary": "The live Image Generation API and tutorial allow Seedream 4.0 up to 14 reference images, while the older dedicated model card still describes multi-image inputs as 2-10." }, { "handling": "Record JPEG only from the model-specific capability tables; do not promote PNG from inconsistent examples.", "path": "capability_profiles.delivery_profiles.formats", "source_ids": [ "model-page", "image-api", "image-guide" ], "summary": "The model card, tutorial capability matrix, and current API parameter table identify JPEG as Seedream 4.0's output format, but several official tutorial code examples still pass output_format=png for this model." } ], "documentation_state": "documented", "model": { "id": "bytedance/seedream-4-0", "lab": "ByteDance", "modality": "image", "name": "Seedream 4.0", "source_ids": [ "lab-page", "model-page", "model-list", "image-api" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0, "denomination": "USD", "id": "input-image", "kind": "metered", "per": 1, "qualifier": "BytePlus lists input images as free.", "source_ids": [ "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0.03, "denomination": "USD", "id": "output-image", "kind": "metered", "per": 1, "qualifier": "Batch requests are billed by the actual number of successfully generated images; outputs rejected by moderation or otherwise unsuccessful are not billed.", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "successfully_generated_image" } ], "source_ids": [ "model-page", "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "lab-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://seed.bytedance.com/en/seedream4_0" }, { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1824718" }, { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "image-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1541523" }, { "id": "image-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1824121" }, { "id": "prompt-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1829186" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "image-api", "model-list", "pricing" ], "value": "seedream-4-5-251128" } ], "capability_profiles": [ { "api_mode": "sequential_image_generation=disabled", "controls": [ { "mode": "exact_set", "name": "size_preset", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "2K", "4K" ] }, { "default": "true", "mode": "exact_set", "name": "watermark", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "name": "guidance_scale", "source_ids": [ "image-api" ], "state": "unsupported" }, { "default": "standard", "mode": "exact_set", "name": "prompt_optimization_mode", "source_ids": [ "image-api" ], "state": "supported", "unsupported_values": [ "fast" ], "values": [ "standard" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "url", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "base64-json", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" }, { "default_format": "jpeg", "endpoint": "POST /api/v3/images/generations", "formats": [ "jpeg" ], "id": "server-sent-events", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "server_sent_events" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "size": { "default": "2048x2048", "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "16:9", "height": 1600, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2848 }, { "aspect_ratio": "9:16", "height": 2848, "source_ids": [ "image-api" ], "unit": "pixel", "width": 1600 }, { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "image-api" ], "unit": "pixel", "width": 4096 }, { "aspect_ratio": "16:9", "height": 3040, "source_ids": [ "image-api" ], "unit": "pixel", "width": 5504 }, { "aspect_ratio": "9:16", "height": 5504, "source_ids": [ "image-api" ], "unit": "pixel", "width": 3040 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 16777216, "min_total_pixels": 3686400, "mode": "range", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "image-api", "image-guide" ], "task": "text_to_image", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } }, { "api_mode": "sequential_image_generation=disabled", "controls": [ { "mode": "exact_set", "name": "size_preset", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "2K", "4K" ] }, { "default": "true", "mode": "exact_set", "name": "watermark", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "name": "guidance_scale", "source_ids": [ "image-api" ], "state": "unsupported" } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "url", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "base64-json", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" }, { "default_format": "jpeg", "endpoint": "POST /api/v3/images/generations", "formats": [ "jpeg" ], "id": "server-sent-events", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "server_sent_events" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>0.0625", "width_to_height_ratio<16", "width_px>14", "height_px>14", "size_bytes<=30000000", "total_pixels<=36000000" ], "encodings": [ "url", "base64_data_url" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 14, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "image-api", "image-guide" ], "state": "supported" } ], "size": { "default": "2048x2048", "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "16:9", "height": 1600, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2848 }, { "aspect_ratio": "9:16", "height": 2848, "source_ids": [ "image-api" ], "unit": "pixel", "width": 1600 }, { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "image-api" ], "unit": "pixel", "width": 4096 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 16777216, "min_total_pixels": 3686400, "mode": "range", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "model-page", "image-api", "image-guide" ], "task": "image_edit", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } }, { "api_mode": "sequential_image_generation=auto", "controls": [ { "default": 15, "max": 15, "min": 1, "mode": "range", "name": "maximum_output_images", "source_ids": [ "image-api" ], "state": "supported", "step": 1, "unit": "image" } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /api/v3/images/generations", "formats": [ "jpeg" ], "id": "server-sent-events", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "server_sent_events" }, { "default_format": "jpeg", "formats": [ "jpeg" ], "id": "buffered-url", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "url" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "batch-image-generation", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "input_image_count+generated_image_count<=15", "width_to_height_ratio>0.0625", "width_to_height_ratio<16", "width_px>14", "height_px>14", "size_bytes<=30000000", "total_pixels<=36000000" ], "encodings": [ "url", "base64_data_url" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 14, "media_type": "image", "min_count": 0, "role": "image_reference", "source_ids": [ "image-api", "image-guide" ], "state": "supported" } ], "size": { "default": "2048x2048", "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "image-api" ], "unit": "pixel", "width": 4096 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 16777216, "min_total_pixels": 3686400, "mode": "range", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "image-api", "image-guide" ], "task": "batch_image_generation" } ], "documentation_state": "documented", "model": { "id": "bytedance/seedream-4-5", "lab": "ByteDance", "modality": "image", "name": "Seedream 4.5", "source_ids": [ "model-page", "model-list", "release-notes" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0, "denomination": "USD", "id": "input-image", "kind": "metered", "per": 1, "qualifier": "BytePlus lists image inputs as free.", "source_ids": [ "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0.04, "denomination": "USD", "id": "output-image", "kind": "metered", "per": 1, "qualifier": "Batch requests are billed by the actual number of images successfully generated; outputs rejected by moderation or otherwise unsuccessful are not billed.", "source_ids": [ "pricing" ], "state": "known", "unit": "successfully_generated_image" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://seed.bytedance.com/en/seedream4_5" }, { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "image-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1541523" }, { "id": "image-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1824121" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2172655" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "image-api", "image-guide", "pricing" ], "value": "seedream-5-0-lite-260128" } ], "capability_profiles": [ { "api_mode": "sequential_image_generation=disabled", "controls": [ { "mode": "exact_set", "name": "size_preset", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "2K", "3K", "4K" ] }, { "default": "jpeg", "mode": "exact_set", "name": "output_format", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "jpeg", "png" ] }, { "default": "true", "mode": "exact_set", "name": "watermark", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "name": "guidance_scale", "source_ids": [ "image-api" ], "state": "unsupported" }, { "default": "standard", "mode": "exact_set", "name": "prompt_optimization_mode", "source_ids": [ "image-api" ], "state": "supported", "unsupported_values": [ "fast" ], "values": [ "standard" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "url", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "base64-json", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" }, { "default_format": "jpeg", "endpoint": "POST /api/v3/images/generations", "formats": [ "jpeg", "png" ], "id": "server-sent-events", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "server_sent_events" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "size": { "default": "2048x2048", "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "16:9", "height": 1600, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2848 }, { "aspect_ratio": "9:16", "height": 2848, "source_ids": [ "image-api" ], "unit": "pixel", "width": 1600 }, { "aspect_ratio": "1:1", "height": 3072, "source_ids": [ "image-api" ], "unit": "pixel", "width": 3072 }, { "aspect_ratio": "16:9", "height": 2304, "source_ids": [ "image-api" ], "unit": "pixel", "width": 4096 }, { "aspect_ratio": "9:16", "height": 4096, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2304 }, { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "image-api" ], "unit": "pixel", "width": 4096 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 16777216, "min_total_pixels": 3686400, "mode": "range", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "image-api", "image-guide" ], "task": "text_to_image", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } }, { "api_mode": "sequential_image_generation=disabled", "controls": [ { "mode": "exact_set", "name": "size_preset", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "2K", "3K", "4K" ] }, { "default": "jpeg", "mode": "exact_set", "name": "output_format", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "jpeg", "png" ] }, { "default": "true", "mode": "exact_set", "name": "watermark", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "name": "guidance_scale", "source_ids": [ "image-api" ], "state": "unsupported" } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "url", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "base64-json", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" }, { "default_format": "jpeg", "endpoint": "POST /api/v3/images/generations", "formats": [ "jpeg", "png" ], "id": "server-sent-events", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "server_sent_events" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>0.0625", "width_to_height_ratio<16", "width_px>14", "height_px>14", "size_bytes<=30000000", "total_pixels<=36000000" ], "encodings": [ "url", "base64_data_url" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 14, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "image-api", "image-guide" ], "state": "supported" } ], "size": { "default": "2048x2048", "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 3072, "source_ids": [ "image-api" ], "unit": "pixel", "width": 3072 }, { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "image-api" ], "unit": "pixel", "width": 4096 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 16777216, "min_total_pixels": 3686400, "mode": "range", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "image-api", "image-guide" ], "task": "image_edit", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } }, { "api_mode": "sequential_image_generation=auto", "controls": [ { "default": 15, "max": 15, "min": 1, "mode": "range", "name": "maximum_output_images", "source_ids": [ "image-api" ], "state": "supported", "step": 1, "unit": "image" } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /api/v3/images/generations", "formats": [ "jpeg", "png" ], "id": "server-sent-events", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "server_sent_events" }, { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "buffered-url", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "url" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "batch-image-generation", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "input_image_count+generated_image_count<=15", "width_to_height_ratio>0.0625", "width_to_height_ratio<16", "width_px>14", "height_px>14", "size_bytes<=30000000", "total_pixels<=36000000" ], "encodings": [ "url", "base64_data_url" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 14, "media_type": "image", "min_count": 0, "role": "image_reference", "source_ids": [ "image-api", "image-guide" ], "state": "supported" } ], "size": { "default": "2048x2048", "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:1", "height": 3072, "source_ids": [ "image-api" ], "unit": "pixel", "width": 3072 }, { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "image-api" ], "unit": "pixel", "width": 4096 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 16777216, "min_total_pixels": 3686400, "mode": "range", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "image-api", "image-guide" ], "task": "batch_image_generation" } ], "documentation_state": "documented", "model": { "id": "bytedance/seedream-5-0-lite", "lab": "ByteDance", "modality": "image", "name": "Seedream 5.0 Lite", "source_ids": [ "model-page", "model-list" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0, "denomination": "USD", "id": "input-image", "kind": "metered", "per": 1, "qualifier": "BytePlus lists image inputs as free.", "source_ids": [ "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0.035, "denomination": "USD", "id": "output-image", "kind": "metered", "per": 1, "qualifier": "Batch requests are billed by the actual number of images successfully generated; outputs rejected by moderation or otherwise unsuccessful are not billed.", "source_ids": [ "pricing" ], "state": "known", "unit": "successfully_generated_image" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://seed.bytedance.com/en/seedream5_0_lite" }, { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "image-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1541523" }, { "id": "image-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1824121" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "image-api", "image-guide", "pricing" ], "value": "dola-seedream-5-0-pro-260628" } ], "capability_profiles": [ { "controls": [ { "default": "2K", "mode": "exact_set", "name": "size_preset", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "1K", "2K" ] }, { "default": "jpeg", "mode": "exact_set", "name": "output_format", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "jpeg", "png" ] }, { "default": "true", "mode": "exact_set", "name": "watermark", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "standard", "mode": "exact_set", "name": "prompt_optimization_mode", "source_ids": [ "image-api" ], "state": "supported", "values": [ "standard", "fast" ] }, { "name": "sequential_image_generation", "source_ids": [ "image-api" ], "state": "unsupported" }, { "name": "stream", "source_ids": [ "image-api" ], "state": "unsupported" }, { "name": "guidance_scale", "source_ids": [ "image-api" ], "state": "unsupported" } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "url", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "base64-json", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "size": { "default": "2K", "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "image-api" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "16:9", "height": 800, "source_ids": [ "image-api" ], "unit": "pixel", "width": 1424 }, { "aspect_ratio": "9:16", "height": 1424, "source_ids": [ "image-api" ], "unit": "pixel", "width": 800 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "16:9", "height": 1584, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2816 }, { "aspect_ratio": "9:16", "height": 2816, "source_ids": [ "image-api" ], "unit": "pixel", "width": 1584 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 4624220, "min_total_pixels": 921600, "mode": "range", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "model-page", "image-api", "image-guide" ], "task": "text_to_image", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } }, { "controls": [ { "default": "2K", "mode": "exact_set", "name": "size_preset", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "1K", "2K" ] }, { "default": "jpeg", "mode": "exact_set", "name": "output_format", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "jpeg", "png" ] }, { "mode": "exact_set", "name": "interactive_editing_input", "source_ids": [ "model-page", "interactive-edit-guide" ], "state": "supported", "values": [ "point", "bounding_box", "arrow", "annotation" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "url", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "base64-json", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "single-image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>0.0625", "width_to_height_ratio<16", "width_px>14", "height_px>14", "size_bytes<=30000000", "total_pixels<=36000000" ], "encodings": [ "url", "base64_data_url" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "image-api", "image-guide" ], "state": "supported" } ], "size": { "default": "2K", "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "image-api" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 4624220, "min_total_pixels": 921600, "mode": "range", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "model-page", "image-api", "image-guide", "interactive-edit-guide" ], "task": "image_edit", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } }, { "controls": [ { "default": "2K", "mode": "exact_set", "name": "size_preset", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "1K", "2K" ] }, { "default": "jpeg", "mode": "exact_set", "name": "output_format", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "values": [ "jpeg", "png" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "url", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "url" }, { "default_format": "jpeg", "formats": [ "jpeg", "png" ], "id": "base64-json", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "transport": "base64_json" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /api/v3/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "multi-reference-image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "width_to_height_ratio>0.0625", "width_to_height_ratio<16", "width_px>14", "height_px>14", "size_bytes<=30000000", "total_pixels<=36000000" ], "encodings": [ "url", "base64_data_url" ], "formats": [ "jpeg", "png", "webp", "bmp", "tiff", "gif", "heic", "heif" ], "max_count": 10, "media_type": "image", "min_count": 2, "role": "image_reference", "source_ids": [ "image-api", "image-guide" ], "state": "supported" } ], "size": { "default": "2K", "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "image-api" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-api" ], "unit": "pixel", "width": 2048 } ], "max_long_to_short_ratio": 16, "max_total_pixels": 4624220, "min_total_pixels": 921600, "mode": "range", "source_ids": [ "image-api", "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "image-api", "image-guide" ], "task": "multi_reference_image_edit", "text_input": { "source_ids": [ "image-api" ], "state": "unknown" } } ], "documentation_state": "documented", "language_support": { "published_label": "a dozen widely used languages", "scope": "prompt_input", "source_ids": [ "model-page" ], "state": "supported" }, "model": { "id": "bytedance/seedream-5-0-pro", "lab": "ByteDance", "modality": "image", "name": "Seedream 5.0 Pro", "source_ids": [ "model-page", "model-list" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0, "applies_when": [ "input_image_index=first" ], "denomination": "USD", "id": "first-input-image", "kind": "metered", "per": 1, "qualifier": "The first input image in a request is free.", "source_ids": [ "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0.003, "applies_when": [ "input_image_index=second_or_later" ], "denomination": "USD", "id": "additional-input-image", "kind": "metered", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0.045, "applies_when": [ "output_pixels<=2360000" ], "denomination": "USD", "id": "output-image-up-to-2-36mp", "kind": "metered", "per": 1, "qualifier": "Outputs rejected by moderation or otherwise unsuccessful are not billed.", "source_ids": [ "pricing" ], "state": "known", "unit": "successfully_generated_image" }, { "amount": 0.09, "applies_when": [ "output_pixels>2360000" ], "denomination": "USD", "id": "output-image-over-2-36mp", "kind": "metered", "per": 1, "qualifier": "Outputs rejected by moderation or otherwise unsuccessful are not billed.", "source_ids": [ "pricing" ], "state": "known", "unit": "successfully_generated_image" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://seed.bytedance.com/en/seedream5_0_pro" }, { "id": "model-list", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1330310" }, { "id": "image-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1541523" }, { "id": "image-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1824121" }, { "id": "interactive-edit-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/2582775" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.byteplus.com/en/docs/ModelArk/1544106" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "models", "llms-docs" ], "value": "eleven_flash_v2" } ], "capability_profiles": [ { "audio_format_access": [ { "format_ids": [ "mp3_44100_192" ], "minimum_plan": "Creator", "source_ids": [ "tts-reference" ] }, { "format_ids": [ "pcm_44100", "wav_44100" ], "minimum_plan": "Pro", "source_ids": [ "tts-reference" ] } ], "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 22050 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 48 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "tts-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 48000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "family": "alaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] } ], "controls": [ { "max": 4294967295, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "tts-reference" ], "state": "supported", "step": 1, "unit": "integer" }, { "default": "auto", "mode": "exact_set", "name": "apply_text_normalization", "source_ids": [ "tts-reference" ], "state": "supported", "values": [ "auto", "on", "off" ] } ], "delivery_profiles": [ { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-speech/{voice_id}", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "wav_8000", "wav_16000", "wav_22050", "wav_24000", "wav_32000", "wav_44100", "wav_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "buffered-http", "source_ids": [ "tts-reference" ], "state": "supported", "transport": "http_response" }, { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-speech/{voice_id}/stream", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "streaming-http", "source_ids": [ "tts-stream-reference", "streaming-guide" ], "state": "supported", "transport": "http_chunked" }, { "endpoint": "GET /v1/text-to-speech/{voice_id}/stream-input", "id": "websocket-input", "source_ids": [ "websocket-reference", "websocket-guide" ], "state": "supported", "transport": "websocket" } ], "duration": { "source_ids": [ "models" ], "state": "unknown" }, "endpoint": "POST /v1/text-to-speech/{voice_id}", "frame_rate": { "source_ids": [ "models" ], "state": "not_applicable" }, "id": "text-to-speech", "native_audio": { "source_ids": [ "models" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "tts-reference", "websocket-reference" ], "state": "supported" } ], "size": { "source_ids": [ "models" ], "state": "not_applicable" }, "source_ids": [ "tts-reference", "tts-overview" ], "task": "text_to_speech", "text_input": { "max": 30000, "source_ids": [ "models" ], "state": "supported", "unit": "character" }, "timing": { "delivery_profile_ids": [ "buffered-http", "streaming-http" ], "endpoints": [ "POST /v1/text-to-speech/{voice_id}/with-timestamps", "POST /v1/text-to-speech/{voice_id}/stream/with-timestamps" ], "granularity": "character", "metadata": [ "alignment", "normalized_alignment" ], "source_ids": [ "tts-timing-reference", "tts-stream-timing-reference" ], "state": "supported" } } ], "conflicts": [ { "handling": "Use the model-specific English and 30,000-character constraints; retain the broader grouped pricing copy as an official conflict.", "path": "capability_profiles.text-to-speech.text_input.max", "source_ids": [ "models", "pricing" ], "summary": "The grouped Flash/Turbo pricing card advertises 32 languages and a 40,000-character limit, while the model-specific table lists Eleven Flash v2 as English-only with a 30,000-character limit." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "en", "name": "English" } ], "listed_count": 1, "published_label": "English", "scope": "speech_output", "source_ids": [ "models", "llms-docs" ], "state": "supported" }, "model": { "id": "elevenlabs/eleven-flash-v2", "lab": "ElevenLabs", "modality": "audio", "name": "Eleven Flash v2", "source_ids": [ "models", "llms-root", "llms-docs" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.05, "denomination": "USD", "id": "tts-api-input", "kind": "metered", "per": 1000, "profile_id": "text-to-speech", "source_ids": [ "pricing" ], "state": "known", "unit": "input_character" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "models", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/overview/models" }, { "id": "tts-overview", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/overview/capabilities/text-to-speech" }, { "id": "tts-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert.md" }, { "id": "tts-stream-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream.md" }, { "id": "tts-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert-with-timestamps.md" }, { "id": "tts-stream-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream-with-timestamps.md" }, { "id": "websocket-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/v-1-text-to-speech-voice-id-stream-input" }, { "id": "websocket-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/eleven-api/guides/how-to/websockets/realtime-tts" }, { "id": "streaming-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/eleven-api/guides/how-to/text-to-speech/streaming" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/pricing/api?price.platform=api" }, { "id": "llms-root", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/llms.txt" }, { "id": "llms-docs", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://elevenlabs.io/docs/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "models", "llms-docs" ], "value": "eleven_flash_v2_5" } ], "capability_profiles": [ { "audio_format_access": [ { "format_ids": [ "mp3_44100_192" ], "minimum_plan": "Creator", "source_ids": [ "tts-reference" ] }, { "format_ids": [ "pcm_44100", "wav_44100" ], "minimum_plan": "Pro", "source_ids": [ "tts-reference" ] } ], "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 22050 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 48 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "tts-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 48000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "family": "alaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] } ], "controls": [ { "max": 4294967295, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "tts-reference" ], "state": "supported", "step": 1, "unit": "integer" }, { "default": "auto", "mode": "exact_set", "name": "apply_text_normalization", "source_ids": [ "tts-reference" ], "state": "supported", "values": [ "auto", "on", "off" ] } ], "delivery_profiles": [ { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-speech/{voice_id}", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "wav_8000", "wav_16000", "wav_22050", "wav_24000", "wav_32000", "wav_44100", "wav_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "buffered-http", "source_ids": [ "tts-reference" ], "state": "supported", "transport": "http_response" }, { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-speech/{voice_id}/stream", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "streaming-http", "source_ids": [ "tts-stream-reference", "streaming-guide" ], "state": "supported", "transport": "http_chunked" }, { "endpoint": "GET /v1/text-to-speech/{voice_id}/stream-input", "id": "websocket-input", "source_ids": [ "websocket-reference", "websocket-guide" ], "state": "supported", "transport": "websocket" } ], "duration": { "source_ids": [ "models" ], "state": "unknown" }, "endpoint": "POST /v1/text-to-speech/{voice_id}", "frame_rate": { "source_ids": [ "models" ], "state": "not_applicable" }, "id": "text-to-speech", "native_audio": { "source_ids": [ "models" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "tts-reference", "websocket-reference" ], "state": "supported" } ], "size": { "source_ids": [ "models" ], "state": "not_applicable" }, "source_ids": [ "tts-reference", "tts-overview" ], "task": "text_to_speech", "text_input": { "max": 40000, "source_ids": [ "models", "pricing" ], "state": "supported", "unit": "character" }, "timing": { "delivery_profile_ids": [ "buffered-http", "streaming-http" ], "endpoints": [ "POST /v1/text-to-speech/{voice_id}/with-timestamps", "POST /v1/text-to-speech/{voice_id}/stream/with-timestamps" ], "granularity": "character", "metadata": [ "alignment", "normalized_alignment" ], "source_ids": [ "tts-timing-reference", "tts-stream-timing-reference" ], "state": "supported" } } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "en", "name": "English" }, { "code": "ja", "name": "Japanese" }, { "code": "zh", "name": "Chinese" }, { "code": "de", "name": "German" }, { "code": "hi", "name": "Hindi" }, { "code": "fr", "name": "French" }, { "code": "ko", "name": "Korean" }, { "code": "pt", "name": "Portuguese" }, { "code": "it", "name": "Italian" }, { "code": "es", "name": "Spanish" }, { "code": "id", "name": "Indonesian" }, { "code": "nl", "name": "Dutch" }, { "code": "tr", "name": "Turkish" }, { "code": "fil", "name": "Filipino" }, { "code": "pl", "name": "Polish" }, { "code": "sv", "name": "Swedish" }, { "code": "bg", "name": "Bulgarian" }, { "code": "ro", "name": "Romanian" }, { "code": "ar", "name": "Arabic" }, { "code": "cs", "name": "Czech" }, { "code": "el", "name": "Greek" }, { "code": "fi", "name": "Finnish" }, { "code": "hr", "name": "Croatian" }, { "code": "ms", "name": "Malay" }, { "code": "sk", "name": "Slovak" }, { "code": "da", "name": "Danish" }, { "code": "ta", "name": "Tamil" }, { "code": "uk", "name": "Ukrainian" }, { "code": "ru", "name": "Russian" }, { "code": "hu", "name": "Hungarian" }, { "code": "no", "name": "Norwegian" }, { "code": "vi", "name": "Vietnamese" } ], "listed_count": 32, "published_label": "32 languages", "scope": "speech_output", "source_ids": [ "models", "llms-docs" ], "state": "supported" }, "limitations": [ { "id": "default-number-normalization", "source_ids": [ "models" ], "summary": "Numbers, dates, and currencies may not be normalized as expected because Flash v2.5 disables normalization by default for latency; forcing normalization on is limited to Enterprise customers." } ], "model": { "id": "elevenlabs/eleven-flash-v2-5", "lab": "ElevenLabs", "modality": "audio", "name": "Eleven Flash v2.5", "source_ids": [ "models", "llms-root", "llms-docs" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.05, "denomination": "USD", "id": "tts-api-input", "kind": "metered", "per": 1000, "profile_id": "text-to-speech", "source_ids": [ "pricing" ], "state": "known", "unit": "input_character" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "models", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/overview/models" }, { "id": "tts-overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/overview/capabilities/text-to-speech" }, { "id": "tts-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert.md" }, { "id": "tts-stream-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream.md" }, { "id": "tts-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert-with-timestamps.md" }, { "id": "tts-stream-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream-with-timestamps.md" }, { "id": "websocket-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/v-1-text-to-speech-voice-id-stream-input" }, { "id": "websocket-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/eleven-api/guides/how-to/websockets/realtime-tts" }, { "id": "streaming-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/eleven-api/guides/how-to/text-to-speech/streaming" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/pricing/api?price.platform=api" }, { "id": "llms-root", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/llms.txt" }, { "id": "llms-docs", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "models", "tts-reference", "llms-docs" ], "value": "eleven_multilingual_v2" } ], "capability_profiles": [ { "audio_format_access": [ { "format_ids": [ "mp3_44100_192" ], "minimum_plan": "Creator", "source_ids": [ "tts-reference" ] }, { "format_ids": [ "pcm_44100", "wav_44100" ], "minimum_plan": "Pro", "source_ids": [ "tts-reference" ] } ], "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 22050 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 48 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "tts-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 48000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] }, { "family": "alaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "tts-reference", "tts-stream-reference" ] } ], "controls": [ { "max": 4294967295, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "tts-reference" ], "state": "supported", "step": 1, "unit": "integer" }, { "default": "auto", "mode": "exact_set", "name": "apply_text_normalization", "source_ids": [ "tts-reference" ], "state": "supported", "values": [ "auto", "on", "off" ] }, { "name": "language_code", "source_ids": [ "tts-reference", "tts-stream-reference", "websocket-reference" ], "state": "unsupported" } ], "delivery_profiles": [ { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-speech/{voice_id}", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "wav_8000", "wav_16000", "wav_22050", "wav_24000", "wav_32000", "wav_44100", "wav_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "buffered-http", "source_ids": [ "tts-reference" ], "state": "supported", "transport": "http_response" }, { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-speech/{voice_id}/stream", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "streaming-http", "source_ids": [ "tts-stream-reference", "streaming-guide" ], "state": "supported", "transport": "http_chunked" }, { "endpoint": "GET /v1/text-to-speech/{voice_id}/stream-input", "id": "websocket-input", "source_ids": [ "websocket-reference", "websocket-guide" ], "state": "supported", "transport": "websocket" } ], "duration": { "source_ids": [ "models" ], "state": "unknown" }, "endpoint": "POST /v1/text-to-speech/{voice_id}", "frame_rate": { "source_ids": [ "models" ], "state": "not_applicable" }, "id": "text-to-speech", "native_audio": { "source_ids": [ "models" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "tts-reference", "websocket-reference" ], "state": "supported" } ], "size": { "source_ids": [ "models" ], "state": "not_applicable" }, "source_ids": [ "tts-reference", "tts-overview" ], "task": "text_to_speech", "text_input": { "max": 10000, "source_ids": [ "models" ], "state": "supported", "unit": "character" }, "timing": { "delivery_profile_ids": [ "buffered-http", "streaming-http" ], "endpoints": [ "POST /v1/text-to-speech/{voice_id}/with-timestamps", "POST /v1/text-to-speech/{voice_id}/stream/with-timestamps" ], "granularity": "character", "metadata": [ "alignment", "normalized_alignment" ], "source_ids": [ "tts-timing-reference", "tts-stream-timing-reference" ], "state": "supported" } } ], "conflicts": [ { "handling": "Use the model-specific values for this record and retain the grouped pricing-card claims only as conflicting provenance.", "path": "language_support,capability_profiles.text-to-speech.text_input.max", "source_ids": [ "models", "pricing" ], "summary": "The model-specific documentation lists 29 languages and a 10,000-character limit, while the grouped Multilingual v2/v3 pricing card says 32 languages and a 40,000-character limit." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "en", "name": "English" }, { "code": "ja", "name": "Japanese" }, { "code": "zh", "name": "Chinese" }, { "code": "de", "name": "German" }, { "code": "hi", "name": "Hindi" }, { "code": "fr", "name": "French" }, { "code": "ko", "name": "Korean" }, { "code": "pt", "name": "Portuguese" }, { "code": "it", "name": "Italian" }, { "code": "es", "name": "Spanish" }, { "code": "id", "name": "Indonesian" }, { "code": "nl", "name": "Dutch" }, { "code": "tr", "name": "Turkish" }, { "code": "fil", "name": "Filipino" }, { "code": "pl", "name": "Polish" }, { "code": "sv", "name": "Swedish" }, { "code": "bg", "name": "Bulgarian" }, { "code": "ro", "name": "Romanian" }, { "code": "ar", "name": "Arabic" }, { "code": "cs", "name": "Czech" }, { "code": "el", "name": "Greek" }, { "code": "fi", "name": "Finnish" }, { "code": "hr", "name": "Croatian" }, { "code": "ms", "name": "Malay" }, { "code": "sk", "name": "Slovak" }, { "code": "da", "name": "Danish" }, { "code": "ta", "name": "Tamil" }, { "code": "uk", "name": "Ukrainian" }, { "code": "ru", "name": "Russian" } ], "listed_count": 29, "published_label": "29 languages", "scope": "speech_output", "source_ids": [ "models", "llms-docs" ], "state": "supported" }, "model": { "id": "elevenlabs/eleven-multilingual-v2", "lab": "ElevenLabs", "modality": "audio", "name": "Eleven Multilingual v2", "source_ids": [ "models", "llms-root", "llms-docs" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.1, "denomination": "USD", "id": "tts-api-input", "kind": "metered", "per": 1000, "profile_id": "text-to-speech", "source_ids": [ "pricing" ], "state": "known", "unit": "input_character" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "models", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/overview/models" }, { "id": "tts-overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/overview/capabilities/text-to-speech" }, { "id": "tts-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert.md" }, { "id": "tts-stream-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream.md" }, { "id": "tts-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert-with-timestamps.md" }, { "id": "tts-stream-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream-with-timestamps.md" }, { "id": "websocket-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/v-1-text-to-speech-voice-id-stream-input" }, { "id": "websocket-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/eleven-api/guides/how-to/websockets/realtime-tts" }, { "id": "streaming-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/eleven-api/guides/how-to/text-to-speech/streaming" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/pricing/api?price.platform=api" }, { "id": "llms-root", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/llms.txt" }, { "id": "llms-docs", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "models", "compose-reference", "v2-api-release" ], "value": "music_v2" } ], "capability_profiles": [ { "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 22050 ], "source_ids": [ "compose-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 48 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "compose-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "compose-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 128, 192, 240, 320 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 48000 ], "source_ids": [ "compose-reference", "format-changelog" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "compose-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 48000 ], "source_ids": [ "compose-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "compose-reference" ] }, { "family": "alaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "compose-reference" ] } ], "controls": [ { "max": 2147483647, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "compose-reference" ], "state": "supported", "step": 1, "unit": "integer" }, { "default": "false", "mode": "exact_set", "name": "force_instrumental", "source_ids": [ "compose-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "store_for_inpainting", "source_ids": [ "compose-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "formats": [ "mp3" ], "mode": "exact_set", "name": "sign_with_c2pa", "source_ids": [ "compose-reference" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "auto", "endpoint": "POST /v1/music", "formats": [ "auto", "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "mp3_48000_128", "mp3_48000_192", "mp3_48000_240", "mp3_48000_320", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "buffered-audio", "source_ids": [ "compose-reference", "format-changelog" ], "state": "supported", "transport": "http_response" } ], "duration": { "automatic": true, "max": 600, "min": 3, "mode": "range", "source_ids": [ "compose-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v1/music", "frame_rate": { "source_ids": [ "music-overview" ], "state": "not_applicable" }, "id": "music-compose", "native_audio": { "source_ids": [ "music-overview" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "copyright_screening=required", "duration_claim=conflicted" ], "media_type": "audio", "role": "audio_reference", "source_ids": [ "music-overview", "references-release" ], "state": "supported" } ], "size": { "source_ids": [ "music-overview" ], "state": "not_applicable" }, "source_ids": [ "compose-reference", "composition-guide" ], "task": "music_generation", "text_input": { "max": 4100, "source_ids": [ "compose-reference" ], "state": "supported", "unit": "character" } }, { "delivery_profiles": [ { "default_format": "auto", "endpoint": "POST /v1/music/stream", "formats": [ "auto", "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "mp3_48000_128", "mp3_48000_192", "mp3_48000_240", "mp3_48000_320", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "streaming-audio", "source_ids": [ "stream-reference", "format-changelog" ], "state": "supported", "transport": "http_chunked" } ], "duration": { "automatic": true, "max": 600, "min": 3, "mode": "range", "source_ids": [ "stream-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v1/music/stream", "id": "music-stream", "native_audio": { "source_ids": [ "music-overview" ], "state": "not_applicable" }, "source_ids": [ "stream-reference" ], "task": "music_generation", "text_input": { "max": 4100, "source_ids": [ "stream-reference" ], "state": "supported", "unit": "character" } }, { "controls": [ { "default": "false", "mode": "exact_set", "name": "with_timestamps", "source_ids": [ "detailed-reference" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "auto", "endpoint": "POST /v1/music/detailed", "formats": [ "auto", "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "mp3_48000_128", "mp3_48000_192", "mp3_48000_240", "mp3_48000_320", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "multipart-audio-and-metadata", "source_ids": [ "detailed-reference", "format-changelog" ], "state": "supported", "transport": "multipart_mixed" } ], "duration": { "automatic": true, "max": 600, "min": 3, "mode": "range", "source_ids": [ "detailed-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v1/music/detailed", "id": "music-detailed", "source_ids": [ "detailed-reference" ], "task": "music_generation_with_metadata", "text_input": { "max": 4100, "source_ids": [ "detailed-reference" ], "state": "supported", "unit": "character" } }, { "controls": [ { "default": "false", "mode": "exact_set", "name": "with_timestamps", "source_ids": [ "detailed-stream-reference" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "auto", "endpoint": "POST /v1/music/detailed/stream", "formats": [ "auto", "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "mp3_48000_128", "mp3_48000_192", "mp3_48000_240", "mp3_48000_320", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "sse-audio-and-metadata", "source_ids": [ "detailed-stream-reference", "format-changelog" ], "state": "supported", "transport": "server_sent_events" } ], "duration": { "automatic": true, "max": 600, "min": 3, "mode": "range", "source_ids": [ "detailed-stream-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v1/music/detailed/stream", "id": "music-detailed-stream", "source_ids": [ "detailed-stream-reference", "sse-changelog" ], "task": "music_generation_with_metadata", "text_input": { "max": 4100, "source_ids": [ "detailed-stream-reference" ], "state": "supported", "unit": "character" } }, { "controls": [ { "max": 30, "min": 1, "mode": "range", "name": "chunk_count", "source_ids": [ "composition-guide" ], "state": "supported", "step": 1, "unit": "chunk" }, { "max": 120, "min": 3, "mode": "range", "name": "chunk_duration", "source_ids": [ "composition-guide" ], "state": "supported", "unit": "second" }, { "max": 50, "min": 0, "mode": "range", "name": "positive_styles_count", "source_ids": [ "composition-guide" ], "state": "supported", "step": 1, "unit": "style" }, { "max": 50, "min": 0, "mode": "range", "name": "negative_styles_count", "source_ids": [ "composition-guide" ], "state": "supported", "step": 1, "unit": "style" }, { "default": "high", "mode": "exact_set", "name": "context_adherence", "source_ids": [ "composition-guide" ], "state": "supported", "values": [ "low", "medium", "high" ] }, { "max": 30, "min": 0.05, "mode": "range", "name": "conditioning_reference_duration", "source_ids": [ "composition-guide", "inpainting-guide" ], "state": "supported", "unit": "second" }, { "default": "medium", "mode": "exact_set", "name": "conditioning_strength", "source_ids": [ "inpainting-guide" ], "state": "supported", "values": [ "low", "medium", "high", "xhigh" ] } ], "duration": { "automatic": true, "max": 600, "min": 3, "mode": "range", "source_ids": [ "plan-reference", "composition-guide" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v1/music/plan", "id": "composition-plan", "source_ids": [ "plan-reference", "composition-guide" ], "task": "music_composition_plan", "text_input": { "max": 4100, "source_ids": [ "plan-reference" ], "state": "supported", "unit": "character" } }, { "controls": [ { "mode": "exact_set", "name": "extract_composition_plan", "source_ids": [ "upload-reference" ], "state": "supported", "values": [ "music_v1", "music_v2" ] }, { "default": "false", "mode": "exact_set", "name": "with_timestamps", "source_ids": [ "upload-reference" ], "state": "supported", "values": [ "true", "false" ] } ], "duration": { "source_ids": [ "upload-reference" ], "state": "unknown" }, "endpoint": "POST /v1/music/upload", "id": "music-upload", "reference_inputs": [ { "constraints": [ "copyright_screening=required" ], "max_count": 1, "media_type": "audio", "min_count": 1, "role": "audio_reference", "source_ids": [ "upload-reference" ], "state": "supported" } ], "source_ids": [ "upload-reference", "inpainting-guide" ], "task": "music_upload_for_inpainting" }, { "controls": [ { "max": 10, "min": 0, "mode": "range", "name": "style_tag_count", "source_ids": [ "video-to-music-reference" ], "state": "supported", "step": 1, "unit": "tag" } ], "duration": { "source_ids": [ "video-to-music-reference" ], "state": "unknown" }, "endpoint": "POST /v1/music/video-to-music", "id": "video-to-music", "reference_inputs": [ { "constraints": [ "maximum_combined_size=200MB", "duration_scope=combined" ], "duration_unit": "second", "max_count": 10, "max_duration": 600, "media_type": "video", "min_count": 1, "role": "video_reference", "source_ids": [ "video-to-music-reference" ], "state": "supported" } ], "source_ids": [ "video-to-music-reference" ], "task": "video_to_music", "text_input": { "max": 1000, "source_ids": [ "video-to-music-reference" ], "state": "supported", "unit": "character" } } ], "conflicts": [ { "handling": "Use the callable endpoint's 600-second bound only inside endpoint-scoped API profiles; do not generalize it to the UI.", "path": "capability_profiles.*.duration.max", "source_ids": [ "music-overview", "compose-reference", "stream-reference", "detailed-reference", "detailed-stream-reference", "composition-guide" ], "summary": "The Music overview states a five-minute maximum, while the live generation endpoints and v2 composition-plan guide permit a 600-second total." }, { "handling": "Record support and copyright screening, but keep the duration and API request shape unresolved.", "path": "capability_profiles.music-compose.reference_inputs.audio_reference", "source_ids": [ "music-overview", "references-release" ], "summary": "The capability overview says an audio reference may be approximately 30 seconds, while the newer official References release says uploads may be 10 seconds to five minutes and are available through ElevenAPI; no matching parameter reference was published." }, { "handling": "Use exact endpoint enums for API profiles and retain the overview claim only as conflicting provenance.", "path": "capability_profiles.*.delivery_profiles.*.formats", "source_ids": [ "music-overview", "compose-reference", "stream-reference", "detailed-reference", "detailed-stream-reference" ], "summary": "The overview advertises MP3 at 44.1 kHz and WAV, while current endpoint enums include 48 kHz MP3, PCM, Opus, u-law, and A-law but no WAV selector." }, { "handling": "Record the displayed USD per-minute charge and preserve the FAQ wording as a billing conflict.", "path": "pricing.charges.music-api-output", "source_ids": [ "pricing" ], "summary": "The pricing table publishes USD 0.15 per minute, while the pricing FAQ describes Music as billed per generation." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "en", "name": "English" }, { "code": "es", "name": "Spanish" }, { "code": "de", "name": "German" }, { "code": "ja", "name": "Japanese" } ], "list_completeness": "non_exhaustive", "listed_count": 4, "published_label": "English, Spanish, German, Japanese and more", "scope": "native_audio", "source_ids": [ "models", "music-overview" ], "state": "supported" }, "limitations": [ { "id": "audio-reference-not-remixing", "source_ids": [ "music-overview" ], "summary": "Audio Reference guides style and sound; it is not a remixing or genre-transfer tool, and substantially different requested genres may be less reliable." }, { "id": "seed-not-exactly-reproducible", "source_ids": [ "compose-reference" ], "summary": "Using the same seed and parameters does not guarantee exact reproducibility, and output can change across system updates." }, { "id": "copyright-screening", "source_ids": [ "composition-guide", "upload-reference" ], "summary": "Copyrighted prompts, styles, lyrics, and uploaded material can be rejected; an uploaded copyrighted file is still charged half the request cost." } ], "model": { "id": "elevenlabs/eleven-music-v2", "lab": "ElevenLabs", "modality": "audio", "name": "Eleven Music v2", "source_ids": [ "models", "music-overview", "v2-api-release" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.15, "applies_when": [ "model_id=music_v2" ], "denomination": "USD", "id": "music-api-output", "kind": "metered", "per": 1, "qualifier": "Prices exclude taxes, levies, and duties.", "source_ids": [ "pricing" ], "state": "known", "unit": "output_minute" }, { "amount": 0, "denomination": "credit", "id": "composition-plan-request", "kind": "metered", "per": 1, "profile_id": "composition-plan", "qualifier": "The endpoint costs zero credits but is rate-limited.", "source_ids": [ "plan-reference" ], "state": "known", "unit": "request" }, { "amount": 1.5, "denomination": "USD", "id": "music-finetune", "kind": "metered", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "finetune" }, { "id": "music-upload", "profile_id": "music-upload", "qualifier": "The upload endpoint says upload price equals song-generation price, but does not publish a safe upload billing unit; copyrighted uploads are charged half.", "source_ids": [ "upload-reference" ], "state": "unknown" } ], "source_ids": [ "pricing", "plan-reference", "upload-reference" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "models", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/overview/models" }, { "id": "music-overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/overview/capabilities/music" }, { "id": "compose-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/music/compose.md" }, { "id": "stream-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/music/stream.md" }, { "id": "detailed-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/music/compose-detailed.md" }, { "id": "detailed-stream-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/music/compose-detailed-stream.md" }, { "id": "plan-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/music/create-composition-plan.md" }, { "id": "upload-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/music/upload.md" }, { "id": "video-to-music-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/music/video-to-music.md" }, { "id": "composition-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/eleven-api/guides/how-to/music/composition-plans" }, { "id": "inpainting-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/eleven-api/guides/how-to/music/inpainting" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/pricing/api?price.platform=api" }, { "id": "v2-api-release", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/changelog/2026/6/15" }, { "id": "format-changelog", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/changelog/2026/6/22" }, { "id": "sse-changelog", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/changelog/2026/7/6" }, { "id": "references-release", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/blog/introducing-references-sound-control-for-music-v2" }, { "id": "llms-docs", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "models", "api-release" ], "value": "eleven_v3" } ], "capability_profiles": [ { "audio_format_access": [ { "format_ids": [ "mp3_44100_192" ], "minimum_plan": "Creator", "source_ids": [ "tts-reference" ] }, { "format_ids": [ "pcm_44100", "wav_44100" ], "minimum_plan": "Pro", "source_ids": [ "tts-reference" ] } ], "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 22050 ], "source_ids": [ "tts-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 48 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "tts-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "tts-reference" ] }, { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "tts-reference", "dialogue-overview" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "tts-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 48000 ], "source_ids": [ "tts-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "tts-reference" ] }, { "family": "alaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "tts-reference" ] } ], "delivery_profiles": [ { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-speech/{voice_id}", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "wav_8000", "wav_16000", "wav_22050", "wav_24000", "wav_32000", "wav_44100", "wav_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "buffered-http", "source_ids": [ "tts-reference" ], "state": "supported", "transport": "http_response" }, { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-speech/{voice_id}/stream", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "streaming-http", "source_ids": [ "tts-stream-reference" ], "state": "supported", "transport": "http_chunked" }, { "id": "websocket-input", "source_ids": [ "tts-websocket-guide" ], "state": "unsupported", "transport": "websocket" } ], "duration": { "source_ids": [ "models" ], "state": "unknown" }, "endpoint": "POST /v1/text-to-speech/{voice_id}", "frame_rate": { "source_ids": [ "models" ], "state": "not_applicable" }, "id": "text-to-speech", "native_audio": { "source_ids": [ "models" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "tts-reference" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "tts-reference", "openapi" ], "state": "unsupported" }, { "media_type": "image", "role": "image_reference", "source_ids": [ "models" ], "state": "not_applicable" } ], "size": { "source_ids": [ "models" ], "state": "not_applicable" }, "source_ids": [ "tts-reference" ], "task": "text_to_speech", "text_input": { "max": 5000, "source_ids": [ "models" ], "state": "supported", "unit": "character" }, "timing": { "delivery_profile_ids": [ "buffered-http", "streaming-http" ], "endpoints": [ "POST /v1/text-to-speech/{voice_id}/with-timestamps", "POST /v1/text-to-speech/{voice_id}/stream/with-timestamps" ], "granularity": "character", "metadata": [ "alignment", "normalized_alignment" ], "source_ids": [ "tts-timing-reference", "tts-stream-timing-reference" ], "state": "supported" } }, { "audio_format_access": [ { "format_ids": [ "mp3_44100_192" ], "minimum_plan": "Creator", "source_ids": [ "dialogue-reference" ] }, { "format_ids": [ "pcm_44100", "wav_44100" ], "minimum_plan": "Pro", "source_ids": [ "dialogue-reference" ] } ], "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 22050 ], "source_ids": [ "dialogue-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 48 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "dialogue-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "dialogue-reference" ] }, { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "dialogue-reference", "dialogue-overview" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "dialogue-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 48000 ], "source_ids": [ "dialogue-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "dialogue-reference" ] }, { "family": "alaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "dialogue-reference" ] } ], "delivery_profiles": [ { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-dialogue", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "wav_8000", "wav_16000", "wav_22050", "wav_24000", "wav_32000", "wav_44100", "wav_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "buffered-http", "source_ids": [ "dialogue-reference" ], "state": "supported", "transport": "http_response" }, { "default_format": "mp3_44100_128", "endpoint": "POST /v1/text-to-dialogue/stream", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "streaming-http", "source_ids": [ "dialogue-stream-reference" ], "state": "supported", "transport": "http_chunked" } ], "duration": { "source_ids": [ "dialogue-reference" ], "state": "unknown" }, "endpoint": "POST /v1/text-to-dialogue", "frame_rate": { "source_ids": [ "models" ], "state": "not_applicable" }, "id": "text-to-dialogue", "native_audio": { "source_ids": [ "models" ], "state": "not_applicable" }, "reference_inputs": [ { "count_scope": "unique", "max_count": 10, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "dialogue-reference" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "dialogue-reference", "openapi" ], "state": "unsupported" }, { "media_type": "image", "role": "image_reference", "source_ids": [ "models" ], "state": "not_applicable" } ], "size": { "source_ids": [ "models" ], "state": "not_applicable" }, "source_ids": [ "dialogue-overview", "dialogue-reference" ], "task": "text_to_dialogue", "timing": { "delivery_profile_ids": [ "buffered-http", "streaming-http" ], "endpoints": [ "POST /v1/text-to-dialogue/with-timestamps", "POST /v1/text-to-dialogue/stream/with-timestamps" ], "granularity": "character", "metadata": [ "alignment", "normalized_alignment", "voice_segments" ], "source_ids": [ "dialogue-timing-reference", "dialogue-stream-timing-reference" ], "state": "supported" } } ], "conflicts": [ { "handling": "Use 5,000 from the model-specific reference, retain the differently scoped product-card claims as conflicts, and keep the separate output-duration range unknown.", "path": "capability_profiles.text-to-speech.text_input.max", "source_ids": [ "models", "tts-product", "pricing", "openapi" ], "summary": "Official pages publish 5,000, 3,000, and grouped 40,000-character limits, and the anonymous runtime model catalog could not resolve them." }, { "handling": "Use the model-specific published list and retain the grouped pricing claim as conflicting provenance.", "path": "language_support", "source_ids": [ "models", "pricing" ], "summary": "The model reference says 70+ languages and lists 74; the grouped API pricing card says 32." }, { "handling": "Use ten for API selection because it is the callable request constraint.", "path": "capability_profiles.text-to-dialogue.reference_inputs.voice.max_count", "source_ids": [ "dialogue-reference", "dialogue-overview" ], "summary": "The endpoint schema caps unique voice IDs at ten; the dialogue overview FAQ says there is no speaker limit." }, { "handling": "Use available from the dated GA sources.", "path": "model.status", "source_ids": [ "ga-blog", "ga-changelog", "best-practices" ], "summary": "Dated February 2026 sources say generally available and out of alpha, while some best-practices copy still says research preview." }, { "handling": "Use the exact endpoint enums.", "path": "capability_profiles.*.delivery_profiles.*.formats", "source_ids": [ "dialogue-overview", "tts-reference", "dialogue-reference" ], "summary": "The prose PCM description is internally inconsistent with the endpoint format enums." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "afr", "name": "Afrikaans" }, { "code": "ara", "name": "Arabic" }, { "code": "hye", "name": "Armenian" }, { "code": "asm", "name": "Assamese" }, { "code": "aze", "name": "Azerbaijani" }, { "code": "bel", "name": "Belarusian" }, { "code": "ben", "name": "Bengali" }, { "code": "bos", "name": "Bosnian" }, { "code": "bul", "name": "Bulgarian" }, { "code": "cat", "name": "Catalan" }, { "code": "ceb", "name": "Cebuano" }, { "code": "nya", "name": "Chichewa" }, { "code": "hrv", "name": "Croatian" }, { "code": "ces", "name": "Czech" }, { "code": "dan", "name": "Danish" }, { "code": "nld", "name": "Dutch" }, { "code": "eng", "name": "English" }, { "code": "est", "name": "Estonian" }, { "code": "fil", "name": "Filipino" }, { "code": "fin", "name": "Finnish" }, { "code": "fra", "name": "French" }, { "code": "glg", "name": "Galician" }, { "code": "kat", "name": "Georgian" }, { "code": "deu", "name": "German" }, { "code": "ell", "name": "Greek" }, { "code": "guj", "name": "Gujarati" }, { "code": "hau", "name": "Hausa" }, { "code": "heb", "name": "Hebrew" }, { "code": "hin", "name": "Hindi" }, { "code": "hun", "name": "Hungarian" }, { "code": "isl", "name": "Icelandic" }, { "code": "ind", "name": "Indonesian" }, { "code": "gle", "name": "Irish" }, { "code": "ita", "name": "Italian" }, { "code": "jpn", "name": "Japanese" }, { "code": "jav", "name": "Javanese" }, { "code": "kan", "name": "Kannada" }, { "code": "kaz", "name": "Kazakh" }, { "code": "kir", "name": "Kirghiz" }, { "code": "kor", "name": "Korean" }, { "code": "lav", "name": "Latvian" }, { "code": "lin", "name": "Lingala" }, { "code": "lit", "name": "Lithuanian" }, { "code": "ltz", "name": "Luxembourgish" }, { "code": "mkd", "name": "Macedonian" }, { "code": "msa", "name": "Malay" }, { "code": "mal", "name": "Malayalam" }, { "code": "cmn", "name": "Mandarin Chinese" }, { "code": "mar", "name": "Marathi" }, { "code": "nep", "name": "Nepali" }, { "code": "nor", "name": "Norwegian" }, { "code": "pus", "name": "Pashto" }, { "code": "fas", "name": "Persian" }, { "code": "pol", "name": "Polish" }, { "code": "por", "name": "Portuguese" }, { "code": "pan", "name": "Punjabi" }, { "code": "ron", "name": "Romanian" }, { "code": "rus", "name": "Russian" }, { "code": "srp", "name": "Serbian" }, { "code": "snd", "name": "Sindhi" }, { "code": "slk", "name": "Slovak" }, { "code": "slv", "name": "Slovenian" }, { "code": "som", "name": "Somali" }, { "code": "spa", "name": "Spanish" }, { "code": "swa", "name": "Swahili" }, { "code": "swe", "name": "Swedish" }, { "code": "tam", "name": "Tamil" }, { "code": "tel", "name": "Telugu" }, { "code": "tha", "name": "Thai" }, { "code": "tur", "name": "Turkish" }, { "code": "ukr", "name": "Ukrainian" }, { "code": "urd", "name": "Urdu" }, { "code": "vie", "name": "Vietnamese" }, { "code": "cym", "name": "Welsh" } ], "list_completeness": "non_exhaustive", "listed_count": 74, "published_label": "70+ languages", "scope": "speech_output", "source_ids": [ "models" ], "state": "supported" }, "model": { "aliases": [ "ElevenLabs v3" ], "id": "elevenlabs/eleven-v3", "lab": "ElevenLabs", "modality": "audio", "name": "Eleven v3", "source_ids": [ "models", "ga-blog", "ga-changelog", "alias-usage" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.1, "applies_when": [ "task=text_to_speech" ], "denomination": "USD", "id": "tts-api-input", "kind": "metered", "per": 1000, "source_ids": [ "pricing" ], "state": "known", "unit": "input_character" }, { "applies_when": [ "task=text_to_dialogue" ], "id": "dialogue-api-input", "source_ids": [ "pricing" ], "state": "unknown" } ], "source_ids": [ "pricing" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "models", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/overview/models" }, { "id": "ga-blog", "kind": "release_note", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/blog/eleven-v3-is-now-generally-available" }, { "id": "ga-changelog", "kind": "changelog", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/changelog/2026/2/2" }, { "id": "alias-usage", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/blog/introducing-the-elevenlabs-app" }, { "id": "api-release", "kind": "changelog", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/changelog/2025/8/20" }, { "id": "tts-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert.md" }, { "id": "tts-stream-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream.md" }, { "id": "tts-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/convert-with-timestamps" }, { "id": "tts-stream-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/api-reference/text-to-speech/stream-with-timestamps" }, { "id": "dialogue-overview", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/overview/capabilities/text-to-dialogue" }, { "id": "dialogue-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/api-reference/text-to-dialogue/convert.md" }, { "id": "dialogue-stream-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/api-reference/text-to-dialogue/stream.md" }, { "id": "dialogue-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/api-reference/text-to-dialogue/convert-with-timestamps" }, { "id": "dialogue-stream-timing-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/api-reference/text-to-dialogue/stream-with-timestamps" }, { "id": "tts-websocket-guide", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/eleven-api/guides/how-to/websockets/realtime-tts" }, { "id": "tts-product", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/text-to-speech-api" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/pricing/api" }, { "id": "openapi", "kind": "api_schema", "retrieved_on": "2026-08-09", "url": "https://api.elevenlabs.io/openapi.json" }, { "id": "best-practices", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://elevenlabs.io/docs/overview/capabilities/text-to-speech/best-practices" } ] }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "models", "sound-effects-reference" ], "value": "eleven_text_to_sound_v2" } ], "capability_profiles": [ { "audio_format_access": [ { "format_ids": [ "mp3_44100_192" ], "minimum_plan": "Creator", "source_ids": [ "sound-effects-reference" ] }, { "format_ids": [ "pcm_44100" ], "minimum_plan": "Pro", "source_ids": [ "sound-effects-reference" ] } ], "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 22050 ], "source_ids": [ "sound-effects-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 48 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "sound-effects-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "sound-effects-reference" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100, 48000 ], "source_ids": [ "sound-effects-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 96, 128, 192 ], "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 48000 ], "source_ids": [ "sound-effects-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "sound-effects-reference" ] }, { "family": "alaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "sound-effects-reference" ] } ], "controls": [ { "default": "false", "mode": "exact_set", "name": "loop", "source_ids": [ "sound-effects-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": 0.3, "max": 1, "min": 0, "mode": "range", "name": "prompt_influence", "source_ids": [ "sound-effects-reference" ], "state": "supported", "unit": "ratio" } ], "delivery_profiles": [ { "endpoint": "POST /v1/sound-generation", "formats": [ "mp3_22050_32", "mp3_24000_48", "mp3_44100_32", "mp3_44100_64", "mp3_44100_96", "mp3_44100_128", "mp3_44100_192", "pcm_8000", "pcm_16000", "pcm_22050", "pcm_24000", "pcm_32000", "pcm_44100", "pcm_48000", "opus_48000_32", "opus_48000_64", "opus_48000_96", "opus_48000_128", "opus_48000_192", "ulaw_8000", "alaw_8000" ], "id": "audio-download", "source_ids": [ "sound-effects-reference" ], "state": "supported", "transport": "http_response" } ], "duration": { "automatic": true, "max": 30, "min": 0.5, "mode": "range", "source_ids": [ "sound-effects-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v1/sound-generation", "frame_rate": { "source_ids": [ "sound-effects-overview" ], "state": "not_applicable" }, "id": "sound-effect-generation", "native_audio": { "source_ids": [ "sound-effects-overview" ], "state": "not_applicable" }, "size": { "source_ids": [ "sound-effects-overview" ], "state": "not_applicable" }, "source_ids": [ "sound-effects-reference", "sound-effects-overview" ], "task": "sound_effect_generation", "text_input": { "source_ids": [ "sound-effects-reference", "website-product-help" ], "state": "unknown" } } ], "conflicts": [ { "handling": "Use 0.5 seconds for the endpoint-scoped API profile.", "path": "capability_profiles.sound-effect-generation.duration.min", "source_ids": [ "sound-effects-overview", "sound-effects-reference" ], "summary": "The capability overview states a 0.1-second minimum, while the live API parameter table requires at least 0.5 seconds." }, { "handling": "Use the exact request enum for the API profile and retain the overview and response prose as conflicting provenance.", "path": "capability_profiles.sound-effect-generation.delivery_profiles.audio-download.formats", "source_ids": [ "sound-effects-overview", "sound-effects-reference" ], "summary": "The overview says every effect is available as MP3 and non-looping effects as 48 kHz WAV, while the live API enum exposes MP3, PCM, Opus, u-law, and A-law and has no WAV selector; response prose still calls the result MP3." }, { "handling": "Keep the API text limit unknown; do not apply the website UI limit to the API.", "path": "capability_profiles.sound-effect-generation.text_input.max", "source_ids": [ "website-product-help", "sound-effects-reference" ], "summary": "The website product UI documents a 450-character prompt maximum, while the API parameter table publishes no text maximum." }, { "handling": "Preserve all official charge representations with their conditions; do not convert credits or infer equivalence.", "path": "pricing", "source_ids": [ "pricing", "credits-pricing" ], "summary": "The current API pricing page publishes USD 0.12 per minute and says Sound Effects is billed per generation, while the product-specific API billing page publishes 100 credits per automatic-duration generation or 11 credits per specified second." } ], "documentation_state": "documented", "limitations": [ { "id": "complex-sequences-best-composed", "source_ids": [ "prompting-help" ], "summary": "The model understands multi-effect sequences, but ElevenLabs recommends generating individual effects and combining them in an audio editor for best results." } ], "model": { "id": "elevenlabs/sound-effects-v2", "lab": "ElevenLabs", "modality": "audio", "name": "Sound effects", "source_ids": [ "models", "sound-effects-overview", "sound-effects-reference" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 0.12, "denomination": "USD", "id": "sound-effects-api-output", "kind": "metered", "per": 1, "profile_id": "sound-effect-generation", "qualifier": "Prices exclude taxes, levies, and duties.", "source_ids": [ "pricing" ], "state": "known", "unit": "output_minute" }, { "amount": 100, "applies_when": [ "duration=automatic" ], "denomination": "credit", "id": "sound-effects-api-automatic-duration", "kind": "metered", "per": 1, "profile_id": "sound-effect-generation", "qualifier": "One sound effect is returned per API generation.", "source_ids": [ "credits-pricing" ], "state": "known", "unit": "generation" }, { "amount": 11, "applies_when": [ "duration=specified" ], "denomination": "credit", "id": "sound-effects-api-specified-duration", "kind": "metered", "per": 1, "profile_id": "sound-effect-generation", "qualifier": "Text-input length does not affect the charge.", "source_ids": [ "credits-pricing" ], "state": "known", "unit": "output_second" } ], "source_ids": [ "pricing", "credits-pricing" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "models", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/overview/models" }, { "id": "sound-effects-overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/overview/capabilities/sound-effects" }, { "id": "sound-effects-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/api-reference/text-to-sound-effects/convert.md" }, { "id": "website-product-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.elevenlabs.io/hc/en-us/articles/25735182995985-What-is-Sound-Effects" }, { "id": "prompting-help", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.elevenlabs.io/hc/en-us/articles/25735604945041-How-do-I-prompt-for-sound-effects" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/pricing/api?price.platform=api" }, { "id": "credits-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/help-center/product/content-production/sound-effects/how-much-does-it-cost-to-generate-sound-effects" }, { "id": "llms-docs", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://elevenlabs.io/docs/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "image-guide", "pricing" ], "value": "gemini-2.5-flash-image" } ], "capability_profiles": [ { "api_mode": "gemini-2.5-flash-image", "controls": [ { "default": "text_and_image", "mode": "exact_set", "name": "response_modalities", "source_ids": [ "image-guide" ], "state": "supported", "values": [ "text_and_image", "image_only" ] }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "65536" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "32768" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /v1beta/interactions", "formats": [ "jpeg" ], "id": "interactions-inline", "source_ids": [ "interactions-api" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "interactions-text-to-image", "native_audio": { "source_ids": [ "model-page", "image-guide" ], "state": "not_applicable" }, "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "2:3", "height": 1248, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 832 }, { "aspect_ratio": "3:2", "height": 832, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1248 }, { "aspect_ratio": "3:4", "height": 1184, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 864 }, { "aspect_ratio": "4:3", "height": 864, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1184 }, { "aspect_ratio": "4:5", "height": 1152, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 896 }, { "aspect_ratio": "5:4", "height": 896, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1152 }, { "aspect_ratio": "9:16", "height": 1344, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 768 }, { "aspect_ratio": "16:9", "height": 768, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1344 }, { "aspect_ratio": "21:9", "height": 672, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1536 } ], "id": "1K", "source_ids": [ "image-guide" ] } ], "source_ids": [ "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "image-guide", "interactions-api" ], "task": "text_to_image" }, { "api_mode": "gemini-2.5-flash-image", "controls": [ { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "65536" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "32768" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /v1beta/interactions", "formats": [ "jpeg" ], "id": "interactions-inline", "source_ids": [ "interactions-api" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "interactions-image-edit", "native_audio": { "source_ids": [ "model-page", "image-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "recommended_count_less_than_or_equal_to=3" ], "formats": [ "png", "jpeg", "webp", "heic", "heif", "gif", "bmp", "tiff" ], "max_count_state": "unknown", "media_type": "image", "min_count": 1, "role": "all_image_references", "source_ids": [ "image-guide", "interactions-api" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "model-page", "image-guide" ], "state": "unsupported" }, { "media_type": "video", "role": "video_reference", "source_ids": [ "model-page", "image-guide" ], "state": "unsupported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "image-guide" ] } ], "source_ids": [ "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "image-guide", "interactions-api" ], "task": "image_edit" }, { "api_mode": "gemini-2.5-flash-image", "controls": [ { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "65536" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "32768" ] } ], "delivery_profiles": [ { "endpoint": "POST /v1beta/models/{model}:generateContent", "formats": [ "png" ], "id": "generate-content-inline", "source_ids": [ "legacy-guide" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "generate-content-image-generation", "native_audio": { "source_ids": [ "model-page", "legacy-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "recommended_count_less_than_or_equal_to=3" ], "max_count_state": "unknown", "media_type": "image", "min_count": 1, "role": "all_image_references", "source_ids": [ "legacy-guide", "image-guide" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "model-page", "legacy-guide" ], "state": "unsupported" }, { "media_type": "video", "role": "video_reference", "source_ids": [ "model-page", "legacy-guide" ], "state": "unsupported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "legacy-guide", "image-guide" ] } ], "source_ids": [ "legacy-guide", "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "legacy-guide", "generate-content-api" ], "task": "multimodal_image_generation" } ], "conflicts": [ { "handling": "Keep the formats scoped to their serving endpoints rather than selecting a single model-wide output format.", "path": "capability_profiles.*.delivery_profiles.*.formats", "source_ids": [ "interactions-api", "legacy-guide" ], "summary": "The Interactions API response-format reference lists JPEG, while official GenerateContent guide examples return PNG." }, { "handling": "Use the image-model-specific API surface and mark audio and video references unsupported on these profiles; do not transfer base-model modalities to the image endpoint.", "path": "capability_profiles.*.reference_inputs.video_reference,capability_profiles.*.reference_inputs.audio_reference", "source_ids": [ "model-card", "model-page", "image-guide" ], "summary": "The Gemini 2.5 Flash model card describes the broader base model as accepting audio and video, while the image-model page and image-generation guide expose text and image inputs for this image endpoint." }, { "handling": "Keep output-count constraints unknown rather than inferring a limit.", "path": "capability_profiles.*.controls.output_count", "source_ids": [ "image-guide" ], "summary": "Google says the model may not follow an exact requested image count and publishes no dependable model-specific maximum." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "EN", "name": "English" }, { "code": "ar-EG", "name": "Arabic (Egypt)" }, { "code": "de-DE", "name": "German (Germany)" }, { "code": "es-MX", "name": "Spanish (Mexico)" }, { "code": "fr-FR", "name": "French (France)" }, { "code": "hi-IN", "name": "Hindi (India)" }, { "code": "id-ID", "name": "Indonesian (Indonesia)" }, { "code": "it-IT", "name": "Italian (Italy)" }, { "code": "ja-JP", "name": "Japanese (Japan)" }, { "code": "ko-KR", "name": "Korean (South Korea)" }, { "code": "pt-BR", "name": "Portuguese (Brazil)" }, { "code": "ru-RU", "name": "Russian (Russia)" }, { "code": "ua-UA", "name": "Ukrainian (Ukraine)" }, { "code": "vi-VN", "name": "Vietnamese (Vietnam)" }, { "code": "zh-CN", "name": "Chinese (China)" } ], "listed_count": 15, "published_label": "Best performance languages", "scope": "prompt_input", "source_ids": [ "image-guide" ], "state": "supported" }, "limitations": [ { "id": "long-form-text-rendering", "source_ids": [ "model-card" ], "summary": "Google reports limitations when rendering long-form text in generated images." }, { "id": "fine-detail-factuality", "source_ids": [ "model-card" ], "summary": "Google reports that fine image details may not be represented factually." }, { "id": "output-count-following", "source_ids": [ "image-guide" ], "summary": "Google says the model may not follow an exact requested number of output images." } ], "model": { "aliases": [ "Nano Banana" ], "id": "google/gemini-2-5-flash-image", "lab": "Google", "modality": "image", "name": "Gemini 2.5 Flash Image", "source_ids": [ "model-page", "image-guide", "model-card", "changelog" ], "status": "available" }, "pricing": { "charges": [ { "amount": 1290, "applies_when": [ "size=1K" ], "denomination": "image_output_token", "id": "image-token-usage-1k", "kind": "usage_increment", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.3, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 30, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-image-output-tokens", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 0.039, "applies_when": [ "service=standard", "size=1K" ], "denomination": "USD", "id": "standard-image-output", "kind": "metered", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.15, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 0.0195, "applies_when": [ "service=batch", "size=1K" ], "denomination": "USD", "id": "batch-image-output", "kind": "metered", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.15, "applies_when": [ "service=flex" ], "denomination": "USD", "id": "flex-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 0.0195, "applies_when": [ "service=flex", "size=1K" ], "denomination": "USD", "id": "flex-image-output", "kind": "metered", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.54, "applies_when": [ "service=priority" ], "denomination": "USD", "id": "priority-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 0.0702, "applies_when": [ "service=priority", "size=1K" ], "denomination": "USD", "id": "priority-image-output", "kind": "metered", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-image" }, { "id": "image-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/image-generation" }, { "id": "legacy-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/generate-content/image-generation" }, { "id": "interactions-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/interactions-api-v1" }, { "id": "generate-content-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/generate-content" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/changelog" }, { "id": "model-card", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-2-5-Flash-Model-Card.pdf" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "pricing", "changelog" ], "value": "gemini-2.5-flash-preview-tts" } ], "capability_profiles": [ { "api_mode": "gemini-2.5-flash-preview-tts", "audio_formats": [ { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "tts-guide" ] } ], "controls": [ { "mode": "exact_set", "name": "voice", "source_ids": [ "tts-guide" ], "state": "supported", "values": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ] }, { "max": 2, "min": 1, "mode": "range", "name": "speaker_count", "source_ids": [ "tts-guide" ], "state": "supported", "step": 1, "unit": "speaker" }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "8192" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "16384" ] } ], "delivery_profiles": [ { "default_format": "pcm_s16le_24000_mono", "endpoint": "POST /v1beta/interactions", "formats": [ "pcm_s16le_24000_mono" ], "id": "interactions-inline-pcm", "source_ids": [ "tts-guide" ], "state": "supported", "transport": "inline" }, { "id": "interactions-streaming", "source_ids": [ "tts-guide" ], "state": "unsupported", "transport": "http_streaming" } ], "duration": { "source_ids": [ "tts-guide" ], "state": "unknown" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "interactions-text-to-speech", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "source_ids": [ "model-page", "tts-guide", "interactions-api" ], "task": "text_to_speech" }, { "api_mode": "gemini-2.5-flash-preview-tts", "audio_formats": [ { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "legacy-tts-guide" ] } ], "controls": [ { "mode": "exact_set", "name": "voice", "source_ids": [ "tts-guide", "legacy-tts-guide" ], "state": "supported", "values": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ] }, { "max": 2, "min": 1, "mode": "range", "name": "speaker_count", "source_ids": [ "tts-guide", "legacy-tts-guide" ], "state": "supported", "step": 1, "unit": "speaker" }, { "mode": "exact_set", "name": "language_code", "source_ids": [ "generate-content-api" ], "state": "supported", "values": [ "de-DE", "en-AU", "en-GB", "en-IN", "en-US", "es-US", "fr-FR", "hi-IN", "pt-BR", "ar-XA", "es-ES", "fr-CA", "id-ID", "it-IT", "ja-JP", "tr-TR", "vi-VN", "bn-IN", "gu-IN", "kn-IN", "ml-IN", "mr-IN", "ta-IN", "te-IN", "nl-NL", "ko-KR", "cmn-CN", "pl-PL", "ru-RU", "th-TH" ] }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "8192" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "16384" ] } ], "delivery_profiles": [ { "default_format": "pcm_s16le_24000_mono", "endpoint": "POST /v1beta/models/{model}:generateContent", "formats": [ "pcm_s16le_24000_mono" ], "id": "generate-content-inline-pcm", "source_ids": [ "legacy-tts-guide" ], "state": "supported", "transport": "inline" }, { "id": "generate-content-streaming", "source_ids": [ "tts-guide" ], "state": "unsupported", "transport": "http_streaming" } ], "duration": { "source_ids": [ "legacy-tts-guide" ], "state": "unknown" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "generate-content-text-to-speech", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "source_ids": [ "model-page", "legacy-tts-guide", "generate-content-api" ], "task": "text_to_speech" } ], "conflicts": [ { "handling": "Keep the model-specific input and output limits and do not reinterpret the differently scoped session-window claim.", "path": "capability_profiles.*.controls.input_token_limit,capability_profiles.*.controls.output_token_limit", "source_ids": [ "model-page", "tts-guide" ], "summary": "The model page publishes 8,192 input tokens and 16,384 output tokens, while the general TTS guide describes a 32k-token session context window without separating input and output." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "ar", "name": "Arabic" }, { "code": "fil", "name": "Filipino" }, { "code": "bn", "name": "Bangla" }, { "code": "fi", "name": "Finnish" }, { "code": "nl", "name": "Dutch" }, { "code": "gl", "name": "Galician" }, { "code": "en", "name": "English" }, { "code": "ka", "name": "Georgian" }, { "code": "fr", "name": "French" }, { "code": "el", "name": "Greek" }, { "code": "de", "name": "German" }, { "code": "gu", "name": "Gujarati" }, { "code": "hi", "name": "Hindi" }, { "code": "ht", "name": "Haitian Creole" }, { "code": "id", "name": "Indonesian" }, { "code": "he", "name": "Hebrew" }, { "code": "it", "name": "Italian" }, { "code": "hu", "name": "Hungarian" }, { "code": "ja", "name": "Japanese" }, { "code": "is", "name": "Icelandic" }, { "code": "ko", "name": "Korean" }, { "code": "jv", "name": "Javanese" }, { "code": "mr", "name": "Marathi" }, { "code": "kn", "name": "Kannada" }, { "code": "pl", "name": "Polish" }, { "code": "kok", "name": "Konkani" }, { "code": "pt", "name": "Portuguese" }, { "code": "lo", "name": "Lao" }, { "code": "ro", "name": "Romanian" }, { "code": "la", "name": "Latin" }, { "code": "ru", "name": "Russian" }, { "code": "lv", "name": "Latvian" }, { "code": "es", "name": "Spanish" }, { "code": "lt", "name": "Lithuanian" }, { "code": "ta", "name": "Tamil" }, { "code": "lb", "name": "Luxembourgish" }, { "code": "te", "name": "Telugu" }, { "code": "mk", "name": "Macedonian" }, { "code": "th", "name": "Thai" }, { "code": "mai", "name": "Maithili" }, { "code": "tr", "name": "Turkish" }, { "code": "mg", "name": "Malagasy" }, { "code": "uk", "name": "Ukrainian" }, { "code": "ms", "name": "Malay" }, { "code": "vi", "name": "Vietnamese" }, { "code": "ml", "name": "Malayalam" }, { "code": "af", "name": "Afrikaans" }, { "code": "mn", "name": "Mongolian" }, { "code": "sq", "name": "Albanian" }, { "code": "ne", "name": "Nepali" }, { "code": "am", "name": "Amharic" }, { "code": "nb", "name": "Norwegian, Bokmål" }, { "code": "hy", "name": "Armenian" }, { "code": "nn", "name": "Norwegian, Nynorsk" }, { "code": "az", "name": "Azerbaijani" }, { "code": "or", "name": "Odia" }, { "code": "eu", "name": "Basque" }, { "code": "ps", "name": "Pashto" }, { "code": "be", "name": "Belarusian" }, { "code": "fa", "name": "Persian" }, { "code": "bg", "name": "Bulgarian" }, { "code": "pa", "name": "Punjabi" }, { "code": "my", "name": "Burmese" }, { "code": "sr", "name": "Serbian" }, { "code": "ca", "name": "Catalan" }, { "code": "sd", "name": "Sindhi" }, { "code": "ceb", "name": "Cebuano" }, { "code": "si", "name": "Sinhala" }, { "code": "cmn", "name": "Chinese, Mandarin" }, { "code": "sk", "name": "Slovak" }, { "code": "hr", "name": "Croatian" }, { "code": "sl", "name": "Slovenian" }, { "code": "cs", "name": "Czech" }, { "code": "sw", "name": "Swahili" }, { "code": "da", "name": "Danish" }, { "code": "sv", "name": "Swedish" }, { "code": "et", "name": "Estonian" }, { "code": "ur", "name": "Urdu" } ], "listed_count": 78, "published_label": "Supported languages", "scope": "speech_output", "source_ids": [ "tts-guide" ], "state": "supported" }, "limitations": [ { "id": "text-only-input-audio-only-output", "source_ids": [ "tts-guide" ], "summary": "Google says TTS models accept only text input and produce only audio output." }, { "id": "no-streaming", "source_ids": [ "tts-guide" ], "summary": "Google says TTS streaming is unavailable for this model." } ], "model": { "aliases": [ "Gemini 2.5 Flash TTS" ], "id": "google/gemini-2-5-flash-preview-tts", "lab": "Google", "modality": "audio", "name": "Gemini 2.5 Flash Text-to-Speech", "source_ids": [ "model-page", "tts-guide", "pricing", "changelog" ], "status": "preview" }, "pricing": { "charges": [ { "amount": 0.5, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_input_token" }, { "amount": 10, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-audio-output", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "audio_output_token" }, { "amount": 0.25, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_input_token" }, { "amount": 5, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-audio-output", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "audio_output_token" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-flash-preview-tts" }, { "id": "tts-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/speech-generation" }, { "id": "legacy-tts-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/generate-content/speech-generation" }, { "id": "interactions-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/interactions-api-v1" }, { "id": "generate-content-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/generate-content" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/changelog" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "pricing", "changelog" ], "value": "gemini-2.5-pro-preview-tts" } ], "capability_profiles": [ { "api_mode": "gemini-2.5-pro-preview-tts", "audio_formats": [ { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "tts-guide" ] } ], "controls": [ { "mode": "exact_set", "name": "voice", "source_ids": [ "tts-guide" ], "state": "supported", "values": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ] }, { "max": 2, "min": 1, "mode": "range", "name": "speaker_count", "source_ids": [ "tts-guide" ], "state": "supported", "step": 1, "unit": "speaker" }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "8192" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "16384" ] } ], "delivery_profiles": [ { "default_format": "pcm_s16le_24000_mono", "endpoint": "POST /v1beta/interactions", "formats": [ "pcm_s16le_24000_mono" ], "id": "interactions-inline-pcm", "source_ids": [ "tts-guide" ], "state": "supported", "transport": "inline" }, { "id": "interactions-streaming", "source_ids": [ "tts-guide" ], "state": "unsupported", "transport": "http_streaming" } ], "duration": { "source_ids": [ "tts-guide" ], "state": "unknown" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "interactions-text-to-speech", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "source_ids": [ "model-page", "tts-guide", "interactions-api" ], "task": "text_to_speech" }, { "api_mode": "gemini-2.5-pro-preview-tts", "audio_formats": [ { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "legacy-tts-guide" ] } ], "controls": [ { "mode": "exact_set", "name": "voice", "source_ids": [ "tts-guide", "legacy-tts-guide" ], "state": "supported", "values": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ] }, { "max": 2, "min": 1, "mode": "range", "name": "speaker_count", "source_ids": [ "tts-guide", "legacy-tts-guide" ], "state": "supported", "step": 1, "unit": "speaker" }, { "mode": "exact_set", "name": "language_code", "source_ids": [ "generate-content-api" ], "state": "supported", "values": [ "de-DE", "en-AU", "en-GB", "en-IN", "en-US", "es-US", "fr-FR", "hi-IN", "pt-BR", "ar-XA", "es-ES", "fr-CA", "id-ID", "it-IT", "ja-JP", "tr-TR", "vi-VN", "bn-IN", "gu-IN", "kn-IN", "ml-IN", "mr-IN", "ta-IN", "te-IN", "nl-NL", "ko-KR", "cmn-CN", "pl-PL", "ru-RU", "th-TH" ] }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "8192" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "16384" ] } ], "delivery_profiles": [ { "default_format": "pcm_s16le_24000_mono", "endpoint": "POST /v1beta/models/{model}:generateContent", "formats": [ "pcm_s16le_24000_mono" ], "id": "generate-content-inline-pcm", "source_ids": [ "legacy-tts-guide" ], "state": "supported", "transport": "inline" }, { "id": "generate-content-streaming", "source_ids": [ "tts-guide" ], "state": "unsupported", "transport": "http_streaming" } ], "duration": { "source_ids": [ "legacy-tts-guide" ], "state": "unknown" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "generate-content-text-to-speech", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "source_ids": [ "model-page", "legacy-tts-guide", "generate-content-api" ], "task": "text_to_speech" } ], "conflicts": [ { "handling": "Keep the model-specific input and output limits and do not reinterpret the differently scoped session-window claim.", "path": "capability_profiles.*.controls.input_token_limit,capability_profiles.*.controls.output_token_limit", "source_ids": [ "model-page", "tts-guide" ], "summary": "The model page publishes 8,192 input tokens and 16,384 output tokens, while the general TTS guide describes a 32k-token session context window without separating input and output." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "ar", "name": "Arabic" }, { "code": "fil", "name": "Filipino" }, { "code": "bn", "name": "Bangla" }, { "code": "fi", "name": "Finnish" }, { "code": "nl", "name": "Dutch" }, { "code": "gl", "name": "Galician" }, { "code": "en", "name": "English" }, { "code": "ka", "name": "Georgian" }, { "code": "fr", "name": "French" }, { "code": "el", "name": "Greek" }, { "code": "de", "name": "German" }, { "code": "gu", "name": "Gujarati" }, { "code": "hi", "name": "Hindi" }, { "code": "ht", "name": "Haitian Creole" }, { "code": "id", "name": "Indonesian" }, { "code": "he", "name": "Hebrew" }, { "code": "it", "name": "Italian" }, { "code": "hu", "name": "Hungarian" }, { "code": "ja", "name": "Japanese" }, { "code": "is", "name": "Icelandic" }, { "code": "ko", "name": "Korean" }, { "code": "jv", "name": "Javanese" }, { "code": "mr", "name": "Marathi" }, { "code": "kn", "name": "Kannada" }, { "code": "pl", "name": "Polish" }, { "code": "kok", "name": "Konkani" }, { "code": "pt", "name": "Portuguese" }, { "code": "lo", "name": "Lao" }, { "code": "ro", "name": "Romanian" }, { "code": "la", "name": "Latin" }, { "code": "ru", "name": "Russian" }, { "code": "lv", "name": "Latvian" }, { "code": "es", "name": "Spanish" }, { "code": "lt", "name": "Lithuanian" }, { "code": "ta", "name": "Tamil" }, { "code": "lb", "name": "Luxembourgish" }, { "code": "te", "name": "Telugu" }, { "code": "mk", "name": "Macedonian" }, { "code": "th", "name": "Thai" }, { "code": "mai", "name": "Maithili" }, { "code": "tr", "name": "Turkish" }, { "code": "mg", "name": "Malagasy" }, { "code": "uk", "name": "Ukrainian" }, { "code": "ms", "name": "Malay" }, { "code": "vi", "name": "Vietnamese" }, { "code": "ml", "name": "Malayalam" }, { "code": "af", "name": "Afrikaans" }, { "code": "mn", "name": "Mongolian" }, { "code": "sq", "name": "Albanian" }, { "code": "ne", "name": "Nepali" }, { "code": "am", "name": "Amharic" }, { "code": "nb", "name": "Norwegian, Bokmål" }, { "code": "hy", "name": "Armenian" }, { "code": "nn", "name": "Norwegian, Nynorsk" }, { "code": "az", "name": "Azerbaijani" }, { "code": "or", "name": "Odia" }, { "code": "eu", "name": "Basque" }, { "code": "ps", "name": "Pashto" }, { "code": "be", "name": "Belarusian" }, { "code": "fa", "name": "Persian" }, { "code": "bg", "name": "Bulgarian" }, { "code": "pa", "name": "Punjabi" }, { "code": "my", "name": "Burmese" }, { "code": "sr", "name": "Serbian" }, { "code": "ca", "name": "Catalan" }, { "code": "sd", "name": "Sindhi" }, { "code": "ceb", "name": "Cebuano" }, { "code": "si", "name": "Sinhala" }, { "code": "cmn", "name": "Chinese, Mandarin" }, { "code": "sk", "name": "Slovak" }, { "code": "hr", "name": "Croatian" }, { "code": "sl", "name": "Slovenian" }, { "code": "cs", "name": "Czech" }, { "code": "sw", "name": "Swahili" }, { "code": "da", "name": "Danish" }, { "code": "sv", "name": "Swedish" }, { "code": "et", "name": "Estonian" }, { "code": "ur", "name": "Urdu" } ], "listed_count": 78, "published_label": "Supported languages", "scope": "speech_output", "source_ids": [ "tts-guide" ], "state": "supported" }, "limitations": [ { "id": "text-only-input-audio-only-output", "source_ids": [ "tts-guide" ], "summary": "Google says TTS models accept only text input and produce only audio output." }, { "id": "no-streaming", "source_ids": [ "tts-guide" ], "summary": "Google says TTS streaming is unavailable for this model." } ], "model": { "aliases": [ "Gemini 2.5 Pro TTS" ], "id": "google/gemini-2-5-pro-preview-tts", "lab": "Google", "modality": "audio", "name": "Gemini 2.5 Pro Text-to-Speech", "source_ids": [ "model-page", "tts-guide", "pricing", "changelog" ], "status": "preview" }, "pricing": { "charges": [ { "amount": 1, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_input_token" }, { "amount": 20, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-audio-output", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "audio_output_token" }, { "amount": 0.5, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_input_token" }, { "amount": 10, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-audio-output", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "audio_output_token" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-2.5-pro-preview-tts" }, { "id": "tts-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/speech-generation" }, { "id": "legacy-tts-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/generate-content/speech-generation" }, { "id": "interactions-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/interactions-api-v1" }, { "id": "generate-content-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/generate-content" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/changelog" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "gemini-model", "gemini-changelog" ], "value": "gemini-3.1-flash-image" } ], "capability_profiles": [ { "api_mode": "gemini-3.1-flash-image", "controls": [ { "default": "text_and_image", "mode": "exact_set", "name": "response_modalities", "source_ids": [ "image-guide" ], "state": "supported", "values": [ "text_and_image", "image_only" ] }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "gemini-model" ], "state": "supported", "unit": "token", "values": [ "131072" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "gemini-model" ], "state": "supported", "unit": "token", "values": [ "32768" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /v1beta/interactions", "formats": [ "jpeg" ], "id": "interactions-inline", "source_ids": [ "interactions-api" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "id": "interactions-text-to-image", "native_audio": { "source_ids": [ "gemini-model", "image-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "media_type": "audio", "role": "audio_reference", "source_ids": [ "image-guide" ], "state": "unsupported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "examples": [ { "aspect_ratio": "1:1", "height": 512, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 512 }, { "aspect_ratio": "1:4", "height": 1024, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 256 }, { "aspect_ratio": "1:8", "height": 1536, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 192 }, { "aspect_ratio": "2:3", "height": 632, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 424 }, { "aspect_ratio": "3:2", "height": 424, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 632 }, { "aspect_ratio": "3:4", "height": 600, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 448 }, { "aspect_ratio": "4:1", "height": 256, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "4:3", "height": 448, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 600 }, { "aspect_ratio": "4:5", "height": 576, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 464 }, { "aspect_ratio": "5:4", "height": 464, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 576 }, { "aspect_ratio": "8:1", "height": 192, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1536 }, { "aspect_ratio": "9:16", "height": 688, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 384 }, { "aspect_ratio": "16:9", "height": 384, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 688 }, { "aspect_ratio": "21:9", "height": 168, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 792 } ], "id": "512", "label": "0.5K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "1:4", "height": 2048, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 512 }, { "aspect_ratio": "1:8", "height": 3072, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 384 }, { "aspect_ratio": "2:3", "height": 1264, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 848 }, { "aspect_ratio": "3:2", "height": 848, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1264 }, { "aspect_ratio": "3:4", "height": 1200, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 896 }, { "aspect_ratio": "4:1", "height": 512, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "4:3", "height": 896, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1200 }, { "aspect_ratio": "4:5", "height": 1152, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 928 }, { "aspect_ratio": "5:4", "height": 928, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1152 }, { "aspect_ratio": "8:1", "height": 384, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3072 }, { "aspect_ratio": "9:16", "height": 1376, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 768 }, { "aspect_ratio": "16:9", "height": 768, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1376 }, { "aspect_ratio": "21:9", "height": 672, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1584 } ], "id": "1K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:4", "height": 4096, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "1:8", "height": 6144, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 768 }, { "aspect_ratio": "2:3", "height": 2528, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1696 }, { "aspect_ratio": "3:2", "height": 1696, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2528 }, { "aspect_ratio": "3:4", "height": 2400, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1792 }, { "aspect_ratio": "4:1", "height": 1024, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 4096 }, { "aspect_ratio": "4:3", "height": 1792, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2400 }, { "aspect_ratio": "4:5", "height": 2304, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1856 }, { "aspect_ratio": "5:4", "height": 1856, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2304 }, { "aspect_ratio": "8:1", "height": 768, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 6144 }, { "aspect_ratio": "9:16", "height": 2752, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1536 }, { "aspect_ratio": "16:9", "height": 1536, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2752 }, { "aspect_ratio": "21:9", "height": 1344, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3168 } ], "id": "2K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "examples": [ { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 4096 }, { "aspect_ratio": "1:4", "height": 8192, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "1:8", "height": 12288, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1536 }, { "aspect_ratio": "2:3", "height": 5056, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3392 }, { "aspect_ratio": "3:2", "height": 3392, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 5056 }, { "aspect_ratio": "3:4", "height": 4800, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3584 }, { "aspect_ratio": "4:1", "height": 2048, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 8192 }, { "aspect_ratio": "4:3", "height": 3584, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 4800 }, { "aspect_ratio": "4:5", "height": 4608, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3712 }, { "aspect_ratio": "5:4", "height": 3712, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 4608 }, { "aspect_ratio": "8:1", "height": 1536, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 12288 }, { "aspect_ratio": "9:16", "height": 5504, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3072 }, { "aspect_ratio": "16:9", "height": 3072, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 5504 }, { "aspect_ratio": "21:9", "height": 2688, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 6336 } ], "id": "4K", "source_ids": [ "image-guide" ] } ], "source_ids": [ "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-model", "image-guide", "interactions-api" ], "task": "text_to_image" }, { "api_mode": "gemini-3.1-flash-image", "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /v1beta/interactions", "formats": [ "jpeg" ], "id": "interactions-inline", "source_ids": [ "interactions-api" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "id": "interactions-image-edit", "native_audio": { "source_ids": [ "gemini-model", "image-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "formats": [ "png", "jpeg", "webp", "heic", "heif", "gif", "bmp", "tiff" ], "max_count": 14, "media_type": "image", "min_count": 1, "role": "all_image_references", "source_ids": [ "image-guide", "interactions-api" ], "state": "supported" }, { "constraints": [ "high_fidelity_preservation=true", "aggregate_image_limit=14" ], "max_count": 10, "media_type": "image", "min_count": 0, "role": "object_reference", "source_ids": [ "image-guide" ], "state": "supported" }, { "constraints": [ "character_consistency=true", "aggregate_image_limit=14" ], "max_count": 4, "media_type": "image", "min_count": 0, "role": "character_reference", "source_ids": [ "image-guide" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "image-guide" ], "state": "unsupported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "512", "label": "0.5K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "2K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "4K", "source_ids": [ "image-guide" ] } ], "source_ids": [ "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "image-guide", "interactions-api" ], "task": "image_edit" }, { "api_mode": "gemini-3.1-flash-image", "duration": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "id": "interactions-video-to-image", "native_audio": { "source_ids": [ "gemini-model", "image-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "approximate_context_duration_without_audio=25_minutes", "aggregate_video_limit=10" ], "encodings": [ "direct_upload" ], "formats": [ "flv", "mov", "mpeg", "mpegs", "mpg", "mp4", "webm", "wmv", "3gpp" ], "max_count": 10, "media_type": "video", "min_count": 1, "role": "video_reference", "source_ids": [ "image-guide", "agent-model" ], "state": "supported" }, { "encodings": [ "public_youtube_url" ], "max_count": 1, "media_type": "video", "min_count": 0, "role": "youtube_video_reference", "source_ids": [ "image-guide", "agent-model" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "image-guide" ], "state": "unsupported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "512", "label": "0.5K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "2K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "4K", "source_ids": [ "image-guide" ] } ], "source_ids": [ "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-model", "image-guide", "agent-model" ], "task": "video_to_image" }, { "api_mode": "gemini-3.1-flash-image", "delivery_profiles": [ { "endpoint": "POST /v1beta/models/{model}:generateContent", "formats": [ "png" ], "id": "generate-content-inline", "source_ids": [ "legacy-guide" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/gemini-3.1-flash-image:generateContent", "frame_rate": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "id": "generate-content-image-generation", "native_audio": { "source_ids": [ "gemini-model", "image-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 14, "media_type": "image", "min_count": 0, "role": "all_image_references", "source_ids": [ "legacy-guide", "image-guide" ], "state": "supported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "512", "label": "0.5K", "source_ids": [ "legacy-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "legacy-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "2K", "source_ids": [ "legacy-guide" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "4K", "source_ids": [ "legacy-guide" ] } ], "source_ids": [ "legacy-guide", "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "legacy-guide", "generate-content-api" ], "task": "multimodal_image_generation" }, { "api_mode": "gemini-3.1-flash-image", "duration": { "source_ids": [ "agent-model" ], "state": "not_applicable" }, "frame_rate": { "source_ids": [ "agent-model" ], "state": "not_applicable" }, "id": "agent-image-generation", "native_audio": { "source_ids": [ "agent-model" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "inline_file_size_less_than_or_equal_to=7MB", "cloud_storage_file_size_less_than_or_equal_to=30MB", "total_request_input_less_than_or_equal_to=500MB" ], "formats": [ "png", "jpeg", "webp", "heic", "heif" ], "max_count": 14, "media_type": "image", "min_count": 0, "role": "all_image_references", "source_ids": [ "agent-model" ], "state": "supported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "512", "label": "0.5K", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "2K", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9" ], "id": "4K", "source_ids": [ "agent-model" ] } ], "source_ids": [ "agent-model" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "agent-model" ], "task": "image_generation" } ], "conflicts": [ { "handling": "Use the pricing page token counts only for pricing accounting and use Google's direct per-image USD charges rather than deriving prices from the conflicting guide table.", "path": "pricing.charges.pricing-token-usage-*", "source_ids": [ "image-guide", "gemini-pricing", "agent-model" ], "summary": "The image guide lists 747, 1,120, 1,120, and 2,000 output tokens for 512/1K/2K/4K, while pricing and Agent material list 747, 1,120, 1,680, and 2,520." }, { "handling": "Use the more precise Gemini Developer amount and retain the rounding disagreement.", "path": "pricing.charges.standard-output-image-4k.amount", "source_ids": [ "gemini-pricing", "agent-pricing" ], "summary": "Gemini Developer pricing publishes USD 0.151 per 4K image, while Agent pricing rounds the same line to USD 0.15." }, { "handling": "Keep JPEG on Interactions profiles and PNG on the separately scoped GenerateContent profile.", "path": "capability_profiles.*.delivery_profiles.*.formats", "source_ids": [ "interactions-api", "image-guide", "legacy-guide" ], "summary": "The Interactions API response-format reference lists JPEG, while official guide examples request PNG." }, { "handling": "Omit 9:21 until the model-specific API surfaces agree that it is accepted.", "path": "capability_profiles.agent-image-generation.size.options.*.aspect_ratios", "source_ids": [ "agent-model", "image-guide", "interactions-api" ], "summary": "Agent Platform lists an additional 9:21 ratio that is absent from both the model-specific Gemini guide and the Interactions API enum." }, { "handling": "Preserve the exact published dimensions and do not silently normalize the source table.", "path": "capability_profiles.interactions-text-to-image.size.options.512.examples.21:9", "source_ids": [ "image-guide" ], "summary": "Google's table labels the 512-tier value 21:9 but publishes dimensions of 792x168, which do not mathematically match 21:9 or the larger-tier scaling." }, { "handling": "Do not assert a universal grounding capability; keep the disagreement scoped to the serving surfaces.", "path": "capability_profiles.*.search_grounding", "source_ids": [ "gemini-model", "image-guide", "agent-model" ], "summary": "Gemini Developer says search grounding is supported, while the Agent Platform model page says grounding is unsupported." }, { "handling": "Omit a thinking control until the official surfaces agree.", "path": "capability_profiles.*.controls.thinking", "source_ids": [ "image-guide", "gemini-model" ], "summary": "The image guide says thinking is enabled by default and cannot be disabled, while other Google material describes Image Search grounding with thinking on or off." }, { "handling": "Keep output-count constraints unknown rather than inferring a limit.", "path": "capability_profiles.*.controls.output_count", "source_ids": [ "image-guide" ], "summary": "Google says the model may not follow an exact requested image count and publishes no dependable model-specific maximum." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "EN", "name": "English" }, { "code": "ar-EG", "name": "Arabic (Egypt)" }, { "code": "de-DE", "name": "German (Germany)" }, { "code": "es-MX", "name": "Spanish (Mexico)" }, { "code": "fr-FR", "name": "French (France)" }, { "code": "hi-IN", "name": "Hindi (India)" }, { "code": "id-ID", "name": "Indonesian (Indonesia)" }, { "code": "it-IT", "name": "Italian (Italy)" }, { "code": "ja-JP", "name": "Japanese (Japan)" }, { "code": "ko-KR", "name": "Korean (South Korea)" }, { "code": "pt-BR", "name": "Portuguese (Brazil)" }, { "code": "ru-RU", "name": "Russian (Russia)" }, { "code": "ua-UA", "name": "Ukrainian (Ukraine)" }, { "code": "vi-VN", "name": "Vietnamese (Vietnam)" }, { "code": "zh-CN", "name": "Chinese (China)" } ], "listed_count": 15, "published_label": "Best performance languages", "scope": "prompt_input", "source_ids": [ "image-guide" ], "state": "supported" }, "limitations": [ { "id": "small-or-long-text", "source_ids": [ "deepmind-model-card" ], "summary": "Google says very small or long text can be rendered poorly." }, { "id": "character-consistency", "source_ids": [ "deepmind-model-card" ], "summary": "Google says character consistency across generations is not always maintained." }, { "id": "masked-and-doodle-edits", "source_ids": [ "deepmind-model-card" ], "summary": "Google says masked or doodle edits can follow instructions only partially or leave persistent marks." }, { "id": "spatial-reasoning", "source_ids": [ "deepmind-model-card" ], "summary": "Google reports occasional left-right confusion and limitations in spatial or 3D reasoning." }, { "id": "factual-and-world-knowledge", "source_ids": [ "deepmind-model-card" ], "summary": "Google says limited world knowledge can lead to factual inaccuracies in generated images." }, { "id": "latency-and-timeouts", "source_ids": [ "deepmind-model-card" ], "summary": "Google reports that some requests can be slow or time out." } ], "model": { "aliases": [ "Nano Banana 2" ], "id": "google/gemini-3-1-flash-image", "lab": "Google", "modality": "image", "name": "Gemini 3.1 Flash Image", "source_ids": [ "gemini-model", "deepmind-model", "gemini-changelog" ], "status": "available" }, "pricing": { "charges": [ { "amount": 747, "applies_when": [ "size=512" ], "denomination": "image_output_token", "id": "pricing-token-usage-512", "kind": "usage_increment", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 1120, "applies_when": [ "size=1K" ], "denomination": "image_output_token", "id": "pricing-token-usage-1k", "kind": "usage_increment", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 1680, "applies_when": [ "size=2K" ], "denomination": "image_output_token", "id": "pricing-token-usage-2k", "kind": "usage_increment", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 2520, "applies_when": [ "size=4K" ], "denomination": "image_output_token", "id": "pricing-token-usage-4k", "kind": "usage_increment", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.5, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-input", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 3, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-output-text-thinking", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_thinking_output_token" }, { "amount": 60, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-output-image-tokens", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 0.045, "applies_when": [ "service=standard", "size=512" ], "denomination": "USD", "id": "standard-output-image-512", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.067, "applies_when": [ "service=standard", "size=1K" ], "denomination": "USD", "id": "standard-output-image-1k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.101, "applies_when": [ "service=standard", "size=2K" ], "denomination": "USD", "id": "standard-output-image-2k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.151, "applies_when": [ "service=standard", "size=4K" ], "denomination": "USD", "id": "standard-output-image-4k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.25, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-input", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 1.5, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-output-text-thinking", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_thinking_output_token" }, { "amount": 30, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-output-image-tokens", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 0.022, "applies_when": [ "service=batch", "size=512" ], "denomination": "USD", "id": "batch-output-image-512", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.034, "applies_when": [ "service=batch", "size=1K" ], "denomination": "USD", "id": "batch-output-image-1k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.05, "applies_when": [ "service=batch", "size=2K" ], "denomination": "USD", "id": "batch-output-image-2k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.076, "applies_when": [ "service=batch", "size=4K" ], "denomination": "USD", "id": "batch-output-image-4k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" } ], "source_ids": [ "gemini-pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "gemini-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image" }, { "id": "image-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/image-generation" }, { "id": "legacy-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/generate-content/image-generation" }, { "id": "interactions-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/api/interactions-api-v1" }, { "id": "generate-content-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/api/generate-content" }, { "id": "gemini-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "gemini-changelog", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/changelog" }, { "id": "agent-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-1-flash-image" }, { "id": "agent-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, { "id": "deepmind-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://deepmind.google/models/gemini-image/flash/" }, { "id": "deepmind-model-card", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://deepmind.google/models/model-cards/gemini-3-1-flash-image/" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "image-guide", "pricing", "changelog" ], "value": "gemini-3.1-flash-lite-image" } ], "capability_profiles": [ { "api_mode": "gemini-3.1-flash-lite-image", "controls": [ { "default": "text_and_image", "mode": "exact_set", "name": "response_modalities", "source_ids": [ "image-guide" ], "state": "supported", "values": [ "text_and_image", "image_only" ] }, { "mode": "exact_set", "name": "thinking_level", "source_ids": [ "model-page" ], "state": "supported", "values": [ "minimal", "high" ] }, { "name": "search_grounding", "source_ids": [ "model-page" ], "state": "unsupported" }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "65536" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "4096" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /v1beta/interactions", "formats": [ "jpeg" ], "id": "interactions-inline", "source_ids": [ "interactions-api" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "interactions-text-to-image", "native_audio": { "source_ids": [ "model-page", "image-guide" ], "state": "not_applicable" }, "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "model-page" ], "unit": "pixel", "width": 1024 } ], "id": "1K", "source_ids": [ "model-page", "image-guide" ] } ], "source_ids": [ "model-page", "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "image-guide", "interactions-api" ], "task": "text_to_image" }, { "api_mode": "gemini-3.1-flash-lite-image", "controls": [ { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "65536" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "4096" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /v1beta/interactions", "formats": [ "jpeg" ], "id": "interactions-inline", "source_ids": [ "interactions-api" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "interactions-image-edit", "native_audio": { "source_ids": [ "model-page", "image-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "formats": [ "png", "jpeg", "webp", "heic", "heif", "gif", "bmp", "tiff" ], "max_count": 14, "media_type": "image", "min_count": 1, "role": "object_reference", "source_ids": [ "model-page", "image-guide", "interactions-api" ], "state": "supported" }, { "media_type": "image", "role": "character_reference", "source_ids": [ "model-page", "image-guide" ], "state": "not_applicable" }, { "media_type": "image", "role": "style_reference", "source_ids": [ "model-page", "image-guide" ], "state": "not_applicable" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "model-page", "image-guide" ], "state": "unsupported" }, { "media_type": "video", "role": "video_reference", "source_ids": [ "model-page", "image-guide" ], "state": "unsupported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "model-page", "image-guide" ] } ], "source_ids": [ "model-page", "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "image-guide", "interactions-api" ], "task": "image_edit" }, { "api_mode": "gemini-3.1-flash-lite-image", "controls": [ { "mode": "exact_set", "name": "thinking_level", "source_ids": [ "model-page" ], "state": "supported", "values": [ "minimal", "high" ] }, { "name": "search_grounding", "source_ids": [ "model-page" ], "state": "unsupported" }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "65536" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "4096" ] } ], "delivery_profiles": [ { "endpoint": "POST /v1beta/models/{model}:generateContent", "formats": [ "png" ], "id": "generate-content-inline", "source_ids": [ "legacy-guide" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/gemini-3.1-flash-lite-image:generateContent", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "generate-content-image-generation", "native_audio": { "source_ids": [ "model-page", "legacy-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 14, "media_type": "image", "min_count": 1, "role": "object_reference", "source_ids": [ "model-page", "legacy-guide" ], "state": "supported" }, { "media_type": "image", "role": "character_reference", "source_ids": [ "model-page", "legacy-guide" ], "state": "not_applicable" }, { "media_type": "image", "role": "style_reference", "source_ids": [ "model-page", "legacy-guide" ], "state": "not_applicable" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "model-page", "legacy-guide" ], "state": "unsupported" }, { "media_type": "video", "role": "video_reference", "source_ids": [ "model-page", "legacy-guide" ], "state": "unsupported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "model-page", "legacy-guide" ] } ], "source_ids": [ "model-page", "legacy-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "legacy-guide", "generate-content-api" ], "task": "multimodal_image_generation" } ], "conflicts": [ { "handling": "Record only the 10 ratios enumerated on the model-specific page; do not import the four additional ratios from a generic endpoint enum.", "path": "capability_profiles.*.size.options.1K.aspect_ratios", "source_ids": [ "model-page", "interactions-api" ], "summary": "The model page says the 1K tier has 14 aspect ratios but explicitly names only 10 of them." }, { "handling": "Keep the formats scoped to their serving endpoints rather than selecting a single model-wide output format.", "path": "capability_profiles.*.delivery_profiles.*.formats", "source_ids": [ "interactions-api", "legacy-guide" ], "summary": "The Interactions API response-format reference lists JPEG, while official GenerateContent guide examples return PNG." }, { "handling": "Use the model-specific image serving surface and mark audio and video references unsupported on these profiles; retain the broader model-card claim as a conflict.", "path": "capability_profiles.*.reference_inputs.video_reference,capability_profiles.*.reference_inputs.audio_reference", "source_ids": [ "model-card", "model-page", "image-guide" ], "summary": "The DeepMind model card describes broader audio and video comprehension, while the model-specific image API page and task guide expose text and image inputs for image generation." }, { "handling": "Use the model-specific API page limits and retain the differently scoped model-card figures as a conflict.", "path": "capability_profiles.*.controls.input_token_limit,capability_profiles.*.controls.output_token_limit", "source_ids": [ "model-page", "model-card" ], "summary": "The model page publishes 65,536 input tokens and 4,096 output tokens, while the model card describes a broader 1M-token context and 64K text output." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "EN", "name": "English" }, { "code": "ar-EG", "name": "Arabic (Egypt)" }, { "code": "de-DE", "name": "German (Germany)" }, { "code": "es-MX", "name": "Spanish (Mexico)" }, { "code": "fr-FR", "name": "French (France)" }, { "code": "hi-IN", "name": "Hindi (India)" }, { "code": "id-ID", "name": "Indonesian (Indonesia)" }, { "code": "it-IT", "name": "Italian (Italy)" }, { "code": "ja-JP", "name": "Japanese (Japan)" }, { "code": "ko-KR", "name": "Korean (South Korea)" }, { "code": "pt-BR", "name": "Portuguese (Brazil)" }, { "code": "ru-RU", "name": "Russian (Russia)" }, { "code": "ua-UA", "name": "Ukrainian (Ukraine)" }, { "code": "vi-VN", "name": "Vietnamese (Vietnam)" }, { "code": "zh-CN", "name": "Chinese (China)" } ], "listed_count": 15, "published_label": "Best performance languages", "scope": "prompt_input", "source_ids": [ "image-guide" ], "state": "supported" }, "limitations": [ { "id": "hallucinations", "source_ids": [ "model-card" ], "summary": "Google says generated images can contain hallucinated content." }, { "id": "latency-and-timeouts", "source_ids": [ "model-card" ], "summary": "Google reports that some requests can be slow or time out." }, { "id": "small-long-and-page-length-text", "source_ids": [ "model-card" ], "summary": "Google says small, long, or page-length text can render poorly." }, { "id": "character-consistency", "source_ids": [ "model-card" ], "summary": "Google says character consistency across generations is not always maintained." }, { "id": "masked-and-doodle-edits", "source_ids": [ "model-card" ], "summary": "Google says masked or doodle edits can follow instructions only partially or leave persistent marks." }, { "id": "input-copying", "source_ids": [ "model-card" ], "summary": "Google reports infrequent cases where generated output copies and pastes the input image." }, { "id": "spatial-reasoning", "source_ids": [ "model-card" ], "summary": "Google reports occasional left-right confusion and limitations in spatial or 3D reasoning." }, { "id": "factual-and-world-knowledge", "source_ids": [ "model-card" ], "summary": "Google says limited world knowledge can produce factual inaccuracies in generated images." } ], "model": { "aliases": [ "Nano Banana 2 Lite" ], "id": "google/gemini-3-1-flash-lite-image", "lab": "Google", "modality": "image", "name": "Gemini 3.1 Flash Lite Image", "source_ids": [ "model-page", "image-guide", "model-card", "changelog" ], "status": "available" }, "pricing": { "charges": [ { "amount": 1120, "applies_when": [ "size=1K" ], "denomination": "image_output_token", "id": "image-token-usage-1k", "kind": "usage_increment", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.25, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_image_or_video_input_token" }, { "amount": 1.5, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-output-text-thinking", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_or_thinking_output_token" }, { "amount": 30, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-output-image-tokens", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 0.0336, "applies_when": [ "service=standard", "size=1K" ], "denomination": "USD", "id": "standard-output-image-1k", "kind": "metered", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.125, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_image_or_video_input_token" }, { "amount": 0.75, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-output-text-thinking", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_or_thinking_output_token" }, { "amount": 15, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-output-image-tokens", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 0.0168, "applies_when": [ "service=batch", "size=1K" ], "denomination": "USD", "id": "batch-output-image-1k", "kind": "metered", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-lite-image" }, { "id": "image-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/image-generation" }, { "id": "legacy-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/generate-content/image-generation" }, { "id": "interactions-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/interactions-api-v1" }, { "id": "generate-content-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/generate-content" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/changelog" }, { "id": "model-card", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://deepmind.google/models/model-cards/gemini-3-1-flash-lite-image/" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "pricing", "changelog" ], "value": "gemini-3.1-flash-tts-preview" } ], "capability_profiles": [ { "api_mode": "gemini-3.1-flash-tts-preview", "audio_formats": [ { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "tts-guide" ] } ], "controls": [ { "mode": "exact_set", "name": "voice", "source_ids": [ "tts-guide" ], "state": "supported", "values": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ] }, { "max": 2, "min": 1, "mode": "range", "name": "speaker_count", "source_ids": [ "tts-guide" ], "state": "supported", "step": 1, "unit": "speaker" }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "8192" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "16384" ] } ], "delivery_profiles": [ { "default_format": "pcm_s16le_24000_mono", "endpoint": "POST /v1beta/interactions", "formats": [ "pcm_s16le_24000_mono" ], "id": "interactions-inline-pcm", "source_ids": [ "tts-guide" ], "state": "supported", "transport": "inline" }, { "endpoint": "POST /v1beta/interactions with stream=true", "formats": [ "pcm_s16le_24000_mono" ], "id": "interactions-streaming", "source_ids": [ "tts-guide", "interactions-api", "changelog" ], "state": "supported", "transport": "http_streaming" } ], "duration": { "source_ids": [ "tts-guide", "model-card" ], "state": "unknown" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "interactions-text-to-speech", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "source_ids": [ "model-page", "tts-guide", "interactions-api" ], "task": "text_to_speech" }, { "api_mode": "gemini-3.1-flash-tts-preview", "audio_formats": [ { "bit_depth_unit": "bit", "bit_depths": [ 16 ], "encoding": "s16le", "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 24000 ], "source_ids": [ "legacy-tts-guide" ] } ], "controls": [ { "mode": "exact_set", "name": "voice", "source_ids": [ "tts-guide", "legacy-tts-guide" ], "state": "supported", "values": [ "Zephyr", "Puck", "Charon", "Kore", "Fenrir", "Leda", "Orus", "Aoede", "Callirrhoe", "Autonoe", "Enceladus", "Iapetus", "Umbriel", "Algieba", "Despina", "Erinome", "Algenib", "Rasalgethi", "Laomedeia", "Achernar", "Alnilam", "Schedar", "Gacrux", "Pulcherrima", "Achird", "Zubenelgenubi", "Vindemiatrix", "Sadachbia", "Sadaltager", "Sulafat" ] }, { "max": 2, "min": 1, "mode": "range", "name": "speaker_count", "source_ids": [ "tts-guide", "legacy-tts-guide" ], "state": "supported", "step": 1, "unit": "speaker" }, { "mode": "exact_set", "name": "language_code", "source_ids": [ "generate-content-api" ], "state": "supported", "values": [ "de-DE", "en-AU", "en-GB", "en-IN", "en-US", "es-US", "fr-FR", "hi-IN", "pt-BR", "ar-XA", "es-ES", "fr-CA", "id-ID", "it-IT", "ja-JP", "tr-TR", "vi-VN", "bn-IN", "gu-IN", "kn-IN", "ml-IN", "mr-IN", "ta-IN", "te-IN", "nl-NL", "ko-KR", "cmn-CN", "pl-PL", "ru-RU", "th-TH" ] }, { "mode": "exact_set", "name": "input_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "8192" ] }, { "mode": "exact_set", "name": "output_token_limit", "source_ids": [ "model-page" ], "state": "supported", "unit": "token", "values": [ "16384" ] } ], "delivery_profiles": [ { "default_format": "pcm_s16le_24000_mono", "endpoint": "POST /v1beta/models/{model}:generateContent", "formats": [ "pcm_s16le_24000_mono" ], "id": "generate-content-inline-pcm", "source_ids": [ "legacy-tts-guide" ], "state": "supported", "transport": "inline" }, { "endpoint": "POST /v1beta/models/{model}:streamGenerateContent", "formats": [ "pcm_s16le_24000_mono" ], "id": "generate-content-streaming", "source_ids": [ "tts-guide", "legacy-tts-guide", "generate-content-api", "changelog" ], "state": "supported", "transport": "http_streaming" } ], "duration": { "source_ids": [ "legacy-tts-guide", "model-card" ], "state": "unknown" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/{model}:generateContent", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "generate-content-text-to-speech", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "source_ids": [ "model-page", "legacy-tts-guide", "generate-content-api" ], "task": "text_to_speech" } ], "conflicts": [ { "handling": "Keep the model-page limits because they are model-specific API limits and retain the differently scoped official claims as a conflict.", "path": "capability_profiles.*.controls.input_token_limit,capability_profiles.*.controls.output_token_limit", "source_ids": [ "model-page", "tts-guide", "model-card" ], "summary": "The model page publishes 8,192 input tokens and 16,384 output tokens; the general TTS guide describes a 32k-token session window; the model card describes up to 16K text input tokens and 32K audio output tokens." } ], "documentation_state": "documented", "language_support": { "languages": [ { "code": "ar", "name": "Arabic" }, { "code": "fil", "name": "Filipino" }, { "code": "bn", "name": "Bangla" }, { "code": "fi", "name": "Finnish" }, { "code": "nl", "name": "Dutch" }, { "code": "gl", "name": "Galician" }, { "code": "en", "name": "English" }, { "code": "ka", "name": "Georgian" }, { "code": "fr", "name": "French" }, { "code": "el", "name": "Greek" }, { "code": "de", "name": "German" }, { "code": "gu", "name": "Gujarati" }, { "code": "hi", "name": "Hindi" }, { "code": "ht", "name": "Haitian Creole" }, { "code": "id", "name": "Indonesian" }, { "code": "he", "name": "Hebrew" }, { "code": "it", "name": "Italian" }, { "code": "hu", "name": "Hungarian" }, { "code": "ja", "name": "Japanese" }, { "code": "is", "name": "Icelandic" }, { "code": "ko", "name": "Korean" }, { "code": "jv", "name": "Javanese" }, { "code": "mr", "name": "Marathi" }, { "code": "kn", "name": "Kannada" }, { "code": "pl", "name": "Polish" }, { "code": "kok", "name": "Konkani" }, { "code": "pt", "name": "Portuguese" }, { "code": "lo", "name": "Lao" }, { "code": "ro", "name": "Romanian" }, { "code": "la", "name": "Latin" }, { "code": "ru", "name": "Russian" }, { "code": "lv", "name": "Latvian" }, { "code": "es", "name": "Spanish" }, { "code": "lt", "name": "Lithuanian" }, { "code": "ta", "name": "Tamil" }, { "code": "lb", "name": "Luxembourgish" }, { "code": "te", "name": "Telugu" }, { "code": "mk", "name": "Macedonian" }, { "code": "th", "name": "Thai" }, { "code": "mai", "name": "Maithili" }, { "code": "tr", "name": "Turkish" }, { "code": "mg", "name": "Malagasy" }, { "code": "uk", "name": "Ukrainian" }, { "code": "ms", "name": "Malay" }, { "code": "vi", "name": "Vietnamese" }, { "code": "ml", "name": "Malayalam" }, { "code": "af", "name": "Afrikaans" }, { "code": "mn", "name": "Mongolian" }, { "code": "sq", "name": "Albanian" }, { "code": "ne", "name": "Nepali" }, { "code": "am", "name": "Amharic" }, { "code": "nb", "name": "Norwegian, Bokmål" }, { "code": "hy", "name": "Armenian" }, { "code": "nn", "name": "Norwegian, Nynorsk" }, { "code": "az", "name": "Azerbaijani" }, { "code": "or", "name": "Odia" }, { "code": "eu", "name": "Basque" }, { "code": "ps", "name": "Pashto" }, { "code": "be", "name": "Belarusian" }, { "code": "fa", "name": "Persian" }, { "code": "bg", "name": "Bulgarian" }, { "code": "pa", "name": "Punjabi" }, { "code": "my", "name": "Burmese" }, { "code": "sr", "name": "Serbian" }, { "code": "ca", "name": "Catalan" }, { "code": "sd", "name": "Sindhi" }, { "code": "ceb", "name": "Cebuano" }, { "code": "si", "name": "Sinhala" }, { "code": "cmn", "name": "Chinese, Mandarin" }, { "code": "sk", "name": "Slovak" }, { "code": "hr", "name": "Croatian" }, { "code": "sl", "name": "Slovenian" }, { "code": "cs", "name": "Czech" }, { "code": "sw", "name": "Swahili" }, { "code": "da", "name": "Danish" }, { "code": "sv", "name": "Swedish" }, { "code": "et", "name": "Estonian" }, { "code": "ur", "name": "Urdu" } ], "listed_count": 78, "published_label": "Supported languages", "scope": "speech_output", "source_ids": [ "tts-guide" ], "state": "supported" }, "limitations": [ { "id": "text-only-input-audio-only-output", "source_ids": [ "tts-guide" ], "summary": "Google says this TTS model accepts only text input and produces only audio output." }, { "id": "voice-prompt-mismatch", "source_ids": [ "model-card" ], "summary": "Google says the generated voice can fail to match the requested prompt or assigned speaker." }, { "id": "long-output-quality-drift", "source_ids": [ "model-card" ], "summary": "Google says quality and consistency can drift when output continues beyond a few minutes." }, { "id": "text-token-server-errors", "source_ids": [ "model-card" ], "summary": "Google says the model can occasionally return text tokens instead of audio and cause an HTTP 500 response; retrying is advised." }, { "id": "vague-prompt-handling", "source_ids": [ "model-card" ], "summary": "Google says vague prompts can trigger false PROHIBITED_CONTENT rejections or cause instructions to be read aloud." } ], "model": { "aliases": [ "Gemini 3.1 Flash TTS Preview" ], "id": "google/gemini-3-1-flash-tts-preview", "lab": "Google", "modality": "audio", "name": "Gemini 3.1 Flash Text-to-Speech Preview", "source_ids": [ "model-page", "tts-guide", "pricing", "changelog" ], "status": "preview" }, "pricing": { "charges": [ { "amount": 25, "denomination": "audio_output_token", "id": "audio-token-usage", "kind": "usage_increment", "per": 1, "source_ids": [ "pricing" ], "state": "known", "unit": "generated_audio_second" }, { "amount": 1, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_input_token" }, { "amount": 20, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-audio-output", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "audio_output_token" }, { "amount": 0.5, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_input_token" }, { "amount": 10, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-audio-output", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "audio_output_token" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-tts-preview" }, { "id": "tts-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/speech-generation" }, { "id": "legacy-tts-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/generate-content/speech-generation" }, { "id": "interactions-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/interactions-api-v1" }, { "id": "generate-content-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/api/generate-content" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/changelog" }, { "id": "model-card", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://deepmind.google/models/model-cards/gemini-3-1-flash-audio/" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "gemini-model", "gemini-changelog" ], "value": "gemini-3-pro-image" } ], "capability_profiles": [ { "api_mode": "gemini-3-pro-image", "controls": [ { "default": "text_and_image", "mode": "exact_set", "name": "response_modalities", "source_ids": [ "image-guide" ], "state": "supported", "values": [ "text_and_image", "image_only" ] } ], "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /v1beta/interactions", "formats": [ "jpeg" ], "id": "interactions-inline", "source_ids": [ "interactions-api" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "id": "interactions-text-to-image", "native_audio": { "source_ids": [ "gemini-model", "image-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "media_type": "audio", "role": "audio_reference", "source_ids": [ "image-guide" ], "state": "unsupported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "2:3", "height": 1264, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 848 }, { "aspect_ratio": "3:2", "height": 848, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1264 }, { "aspect_ratio": "3:4", "height": 1200, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 896 }, { "aspect_ratio": "4:3", "height": 896, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1200 }, { "aspect_ratio": "4:5", "height": 1152, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 928 }, { "aspect_ratio": "5:4", "height": 928, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1152 }, { "aspect_ratio": "9:16", "height": 1376, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 768 }, { "aspect_ratio": "16:9", "height": 768, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1376 }, { "aspect_ratio": "21:9", "height": 672, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1584 } ], "id": "1K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "2:3", "height": 2528, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1696 }, { "aspect_ratio": "3:2", "height": 1696, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2528 }, { "aspect_ratio": "3:4", "height": 2400, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1792 }, { "aspect_ratio": "4:3", "height": 1792, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2400 }, { "aspect_ratio": "4:5", "height": 2304, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1856 }, { "aspect_ratio": "5:4", "height": 1856, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2304 }, { "aspect_ratio": "9:16", "height": 2752, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1536 }, { "aspect_ratio": "16:9", "height": 1536, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2752 }, { "aspect_ratio": "21:9", "height": 1344, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3168 } ], "id": "2K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "examples": [ { "aspect_ratio": "1:1", "height": 4096, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 4096 }, { "aspect_ratio": "2:3", "height": 5056, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3392 }, { "aspect_ratio": "3:2", "height": 3392, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 5056 }, { "aspect_ratio": "3:4", "height": 4800, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3584 }, { "aspect_ratio": "4:3", "height": 3584, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 4800 }, { "aspect_ratio": "4:5", "height": 4608, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3712 }, { "aspect_ratio": "5:4", "height": 3712, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 4608 }, { "aspect_ratio": "9:16", "height": 5504, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3072 }, { "aspect_ratio": "16:9", "height": 3072, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 5504 }, { "aspect_ratio": "21:9", "height": 2688, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 6336 } ], "id": "4K", "source_ids": [ "image-guide" ] } ], "source_ids": [ "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-model", "image-guide", "interactions-api" ], "task": "text_to_image" }, { "api_mode": "gemini-3-pro-image", "delivery_profiles": [ { "default_format": "jpeg", "endpoint": "POST /v1beta/interactions", "formats": [ "jpeg" ], "id": "interactions-inline", "source_ids": [ "interactions-api" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "frame_rate": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "id": "interactions-image-edit", "native_audio": { "source_ids": [ "gemini-model", "image-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "formats": [ "png", "jpeg", "webp", "heic", "heif", "gif", "bmp", "tiff" ], "max_count": 14, "media_type": "image", "min_count": 1, "role": "all_image_references", "source_ids": [ "image-guide", "interactions-api" ], "state": "supported" }, { "constraints": [ "high_fidelity_preservation=true", "aggregate_image_limit=14" ], "max_count": 6, "media_type": "image", "min_count": 0, "role": "object_reference", "source_ids": [ "image-guide" ], "state": "supported" }, { "constraints": [ "character_consistency=true", "aggregate_image_limit=14" ], "max_count": 5, "media_type": "image", "min_count": 0, "role": "character_reference", "source_ids": [ "image-guide" ], "state": "supported" }, { "constraints": [ "style_transfer=true", "aggregate_image_limit=14" ], "max_count": 3, "media_type": "image", "min_count": 0, "role": "style_reference", "source_ids": [ "image-guide" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "image-guide" ], "state": "unsupported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "2K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "4K", "source_ids": [ "image-guide" ] } ], "source_ids": [ "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "image-guide", "interactions-api" ], "task": "image_edit" }, { "api_mode": "gemini-3-pro-image", "delivery_profiles": [ { "endpoint": "POST /v1beta/models/{model}:generateContent", "formats": [ "png" ], "id": "generate-content-inline", "source_ids": [ "legacy-guide" ], "state": "supported", "transport": "inline" } ], "duration": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/gemini-3-pro-image:generateContent", "frame_rate": { "source_ids": [ "gemini-model" ], "state": "not_applicable" }, "id": "generate-content-image-generation", "native_audio": { "source_ids": [ "gemini-model", "image-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 14, "media_type": "image", "min_count": 0, "role": "all_image_references", "source_ids": [ "legacy-guide", "image-guide" ], "state": "supported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "2K", "source_ids": [ "image-guide" ] }, { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "4K", "source_ids": [ "image-guide" ] } ], "source_ids": [ "legacy-guide", "image-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "legacy-guide", "generate-content-api" ], "task": "multimodal_image_generation" }, { "api_mode": "gemini-3-pro-image", "controls": [ { "max": 2, "min": 0, "mode": "range", "name": "temperature", "source_ids": [ "agent-model" ], "state": "supported" }, { "default": 0.95, "max": 1, "min": 0, "mode": "range", "name": "top_p", "source_ids": [ "agent-model" ], "state": "supported" }, { "default": 64, "mode": "exact_set", "name": "top_k", "source_ids": [ "agent-model" ], "state": "supported", "values": [ "64" ] }, { "default": 1, "mode": "exact_set", "name": "candidate_count", "source_ids": [ "agent-model" ], "state": "supported", "values": [ "1" ] } ], "duration": { "source_ids": [ "agent-model" ], "state": "not_applicable" }, "frame_rate": { "source_ids": [ "agent-model" ], "state": "not_applicable" }, "id": "agent-image-generation", "native_audio": { "source_ids": [ "agent-model" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "inline_file_size_less_than_or_equal_to=7MB", "cloud_storage_file_size_less_than_or_equal_to=30MB", "total_request_input_less_than_or_equal_to=500MB" ], "formats": [ "png", "jpeg", "webp", "heic", "heif" ], "max_count": 14, "media_type": "image", "min_count": 0, "role": "all_image_references", "source_ids": [ "agent-model" ], "state": "supported" } ], "size": { "default": "1K", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "1K", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "2K", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "1:1", "2:3", "3:2", "3:4", "4:3", "4:5", "5:4", "9:16", "16:9", "21:9" ], "id": "4K", "render_modes": [ "preview" ], "source_ids": [ "agent-model" ] } ], "source_ids": [ "agent-model" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "agent-model" ], "task": "image_generation" } ], "conflicts": [ { "handling": "Keep JPEG on Interactions profiles and PNG on the separately scoped GenerateContent profile; do not assert one universal output format.", "path": "capability_profiles.*.delivery_profiles.*.formats", "source_ids": [ "interactions-api", "image-guide", "legacy-guide" ], "summary": "The Interactions API response-format reference lists JPEG, while official model-guide examples request PNG." }, { "handling": "Use six on the typed object-reference role and retain the prose inconsistency.", "path": "capability_profiles.interactions-image-edit.reference_inputs.object_reference.max_count", "source_ids": [ "image-guide" ], "summary": "The typed reference table permits six high-fidelity object images, while another guide paragraph says five high-fidelity images." }, { "handling": "Keep the model available and mark only the Agent 4K size option with its published preview qualifier.", "path": "capability_profiles.agent-image-generation.size.options.4K", "source_ids": [ "gemini-changelog", "agent-model" ], "summary": "The stable model is generally available, while Agent Platform describes 4K output as preview." }, { "handling": "Omit a thinking control until the official surfaces agree.", "path": "capability_profiles.*.controls.thinking", "source_ids": [ "image-guide", "gemini-model" ], "summary": "The image guide describes thinking as enabled by default and not disableable, while other Google material describes search grounding with thinking on or off." }, { "handling": "Keep output-count constraints unknown rather than inferring a limit.", "path": "capability_profiles.*.controls.output_count", "source_ids": [ "image-guide" ], "summary": "Google says the model may not follow an exact requested image count and publishes no dependable model-specific maximum." } ], "documentation_state": "documented", "language_support": { "scope": "prompt_input", "source_ids": [ "gemini-model", "image-guide" ], "state": "unknown" }, "limitations": [ { "id": "small-text-and-fine-details", "source_ids": [ "deepmind-model" ], "summary": "Google says small faces, spelling, and fine image details can remain difficult." }, { "id": "factual-accuracy", "source_ids": [ "deepmind-model" ], "summary": "Google says generated visual content can contain factual inaccuracies." }, { "id": "translation-quality", "source_ids": [ "deepmind-model" ], "summary": "Google says translated image text can have grammatical or cultural errors." }, { "id": "complex-masked-edits", "source_ids": [ "deepmind-model" ], "summary": "Google says complex masked edits can produce blending artifacts." }, { "id": "character-consistency", "source_ids": [ "deepmind-model" ], "summary": "Google says character consistency across generated images can remain imperfect." } ], "model": { "aliases": [ "Nano Banana Pro" ], "id": "google/gemini-3-pro-image", "lab": "Google", "modality": "image", "name": "Gemini 3 Pro Image", "source_ids": [ "gemini-model", "deepmind-model", "gemini-changelog" ], "status": "available" }, "pricing": { "charges": [ { "amount": 560, "denomination": "input_token", "id": "input-image-token-usage", "kind": "usage_increment", "per": 1, "source_ids": [ "gemini-model", "gemini-pricing" ], "state": "known", "unit": "input_image" }, { "amount": 1120, "applies_when": [ "size=1K_or_2K" ], "denomination": "image_output_token", "id": "output-token-usage-1k-2k", "kind": "usage_increment", "per": 1, "source_ids": [ "gemini-model", "image-guide", "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 2000, "applies_when": [ "size=4K" ], "denomination": "image_output_token", "id": "output-token-usage-4k", "kind": "usage_increment", "per": 1, "source_ids": [ "gemini-model", "image-guide", "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 2, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-input", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 12, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-output-text-thinking", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_thinking_output_token" }, { "amount": 0.0011, "applies_when": [ "service=standard", "token_usage=560" ], "denomination": "USD", "id": "standard-input-image-equivalent", "kind": "estimate", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "input_image" }, { "amount": 120, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-output-image-tokens", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 0.134, "applies_when": [ "service=standard", "size=1K_or_2K" ], "denomination": "USD", "id": "standard-output-image-1k-2k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.24, "applies_when": [ "service=standard", "size=4K" ], "denomination": "USD", "id": "standard-output-image-4k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 1, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-input", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 6, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-output-text-thinking", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_thinking_output_token" }, { "amount": 0.0006, "applies_when": [ "service=batch", "token_usage=560" ], "denomination": "USD", "id": "batch-input-image-equivalent", "kind": "estimate", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "input_image" }, { "amount": 60, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-output-image-tokens", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 0.067, "applies_when": [ "service=batch", "size=1K_or_2K" ], "denomination": "USD", "id": "batch-output-image-1k-2k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.12, "applies_when": [ "service=batch", "size=4K" ], "denomination": "USD", "id": "batch-output-image-4k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 1, "applies_when": [ "service=flex" ], "denomination": "USD", "id": "flex-input", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 0.0006, "applies_when": [ "service=flex", "token_usage=560" ], "denomination": "USD", "id": "flex-input-image-equivalent", "kind": "estimate", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "input_image" }, { "amount": 6, "applies_when": [ "service=flex" ], "denomination": "USD", "id": "flex-output-text-thinking", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_thinking_output_token" }, { "amount": 60, "applies_when": [ "service=flex" ], "denomination": "USD", "id": "flex-output-image-tokens", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 0.067, "applies_when": [ "service=flex", "size=1K_or_2K" ], "denomination": "USD", "id": "flex-output-image-1k-2k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.12, "applies_when": [ "service=flex", "size=4K" ], "denomination": "USD", "id": "flex-output-image-4k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_image" }, { "amount": 3.6, "applies_when": [ "service=priority" ], "denomination": "USD", "id": "priority-input", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_image_input_token" }, { "amount": 21.6, "applies_when": [ "service=priority" ], "denomination": "USD", "id": "priority-output-text-thinking", "kind": "metered", "per": 1000000, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "text_or_thinking_output_token" }, { "amount": 216, "applies_when": [ "service=priority" ], "denomination": "USD", "id": "priority-output-image-tokens", "kind": "metered", "per": 1000000, "qualifier": "Google does not publish a per-image priority equivalent.", "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "image_output_token" } ], "source_ids": [ "gemini-pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "gemini-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/models/gemini-3-pro-image" }, { "id": "image-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/image-generation" }, { "id": "legacy-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/generate-content/image-generation" }, { "id": "interactions-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/api/interactions-api-v1" }, { "id": "generate-content-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/api/generate-content" }, { "id": "gemini-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "gemini-changelog", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/changelog" }, { "id": "agent-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-pro-image" }, { "id": "deepmind-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://deepmind.google/models/gemini-image/pro/" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "music-guide", "gemini-changelog" ], "value": "lyria-3-clip-preview" } ], "capability_profiles": [ { "api_mode": "lyria-3-clip-preview", "delivery_profiles": [ { "default_format": "mp3", "formats": [ "mp3" ], "id": "interactions-audio", "source_ids": [ "model-page", "music-guide" ], "state": "supported", "transport": "base64_json" } ], "duration": { "max": 30, "min": 30, "mode": "range", "source_ids": [ "model-page", "music-guide", "gemini-changelog" ], "state": "supported", "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "id": "interactions-music-generation", "native_audio": { "source_ids": [ "model-page", "music-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 10, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "music-guide" ], "state": "supported" } ], "source_ids": [ "model-page", "music-guide" ], "task": "music_generation" } ], "conflicts": [ { "handling": "Keep the exact sample rate unresolved; record only the unambiguous MP3 delivery format.", "path": "capability_profiles.interactions-music-generation.audio_formats", "source_ids": [ "model-page", "music-guide", "gemini-changelog" ], "summary": "The model page and launch changelog state 48 kHz stereo output, while the current music-generation guide states 44.1 kHz stereo output." } ], "documentation_state": "documented", "limitations": [ { "id": "safety-filter-blocking", "source_ids": [ "music-guide" ], "summary": "Google says prompts can be blocked by safety filters, including requests for specific artist voices or copyrighted lyrics." }, { "id": "single-turn-generation", "source_ids": [ "music-guide" ], "summary": "Google says Lyria 3 music generation is single-turn and does not support iterative multi-turn editing or refinement." }, { "id": "non-deterministic-output", "source_ids": [ "music-guide" ], "summary": "Google says results may vary between calls even when the prompt is unchanged." } ], "model": { "id": "google/lyria-3-clip-preview", "lab": "Google", "modality": "audio", "name": "Lyria 3 Clip Preview", "source_ids": [ "model-page", "music-guide", "gemini-changelog" ], "status": "preview" }, "pricing": { "charges": [ { "amount": 0.04, "applies_when": [ "service=gemini_developer", "tier=paid" ], "denomination": "USD", "id": "paid-tier-song", "kind": "metered", "per": 1, "profile_id": "interactions-music-generation", "qualifier": "The pricing table labels this a 30-second song and says the free tier is unavailable.", "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "request" } ], "source_ids": [ "gemini-pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/models/lyria-3-clip-preview" }, { "id": "music-guide", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/music-generation" }, { "id": "gemini-pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "gemini-changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/changelog" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "music-guide", "gemini-pricing", "gemini-changelog" ], "value": "lyria-3-pro-preview" } ], "capability_profiles": [ { "api_mode": "lyria-3-pro-preview", "delivery_profiles": [ { "default_format": "mp3", "formats": [ "mp3", "wav" ], "id": "interactions-audio", "source_ids": [ "model-page", "music-guide" ], "state": "supported", "transport": "base64_json" } ], "duration": { "source_ids": [ "music-guide" ], "state": "unknown" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/interactions", "id": "interactions-music-generation", "native_audio": { "source_ids": [ "model-page", "music-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 10, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "music-guide" ], "state": "supported" } ], "source_ids": [ "model-page", "music-guide" ], "task": "music_generation" } ], "conflicts": [ { "handling": "Keep the exact sample rate unresolved; record only the unambiguous MP3 and WAV delivery formats.", "path": "capability_profiles.interactions-music-generation.audio_formats", "source_ids": [ "model-page", "music-guide", "gemini-changelog" ], "summary": "The model page and launch changelog state 48 kHz stereo output, while the current music-generation guide states 44.1 kHz stereo output." }, { "handling": "Use lyria-3-pro-preview as the callable identifier and preserve the model-page typo as conflicting provenance.", "path": "api_identifiers", "source_ids": [ "model-page", "music-guide", "gemini-pricing", "gemini-changelog" ], "summary": "The Lyria 3 Pro model page labels its model-code row as lyria-3-clip-preview, while the guide, pricing page, changelog, page URL, and examples identify the Pro request value as lyria-3-pro-preview." } ], "documentation_state": "documented", "limitations": [ { "id": "safety-filter-blocking", "source_ids": [ "music-guide" ], "summary": "Google says prompts can be blocked by safety filters, including requests for specific artist voices or copyrighted lyrics." }, { "id": "single-turn-generation", "source_ids": [ "music-guide" ], "summary": "Google says Lyria 3 music generation is single-turn and does not support iterative multi-turn editing or refinement." }, { "id": "non-deterministic-output", "source_ids": [ "music-guide" ], "summary": "Google says results may vary between calls even when the prompt is unchanged." }, { "id": "duration-not-exact", "source_ids": [ "music-guide" ], "summary": "Google describes Pro output as lasting a couple of minutes and says prompts or timestamps can influence duration, but publishes no exact minimum or maximum." } ], "model": { "id": "google/lyria-3-pro-preview", "lab": "Google", "modality": "audio", "name": "Lyria 3 Pro Preview", "source_ids": [ "model-page", "music-guide", "gemini-changelog" ], "status": "preview" }, "pricing": { "charges": [ { "amount": 0.08, "applies_when": [ "service=gemini_developer", "tier=paid" ], "denomination": "USD", "id": "paid-tier-song", "kind": "metered", "per": 1, "profile_id": "interactions-music-generation", "qualifier": "The pricing table labels this a full song and says the free tier is unavailable.", "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "request" } ], "source_ids": [ "gemini-pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/models/lyria-3-pro-preview" }, { "id": "music-guide", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/music-generation" }, { "id": "gemini-pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "gemini-changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/changelog" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "gemini-model", "gemini-guide" ], "value": "veo-3.1-generate-preview" }, { "kind": "model_id", "source_ids": [ "agent-model" ], "value": "veo-3.1-generate-001" } ], "capability_profiles": [ { "api_mode": "veo-3.1-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_all" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 1, "unit": "video" } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "gemini-mp4", "source_ids": [ "gemini-guide" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 2, "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-text-to-video", "native_audio": { "default": true, "source_ids": [ "gemini-model", "gemini-guide" ], "state": "supported" }, "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-model", "gemini-guide" ], "task": "text_to_video" }, { "api_mode": "veo-3.1-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_adult" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 1, "unit": "video" } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "gemini-mp4", "source_ids": [ "gemini-guide" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 2, "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-image-to-video", "native_audio": { "default": true, "source_ids": [ "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-guide" ], "task": "image_to_video" }, { "api_mode": "veo-3.1-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_adult" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 1, "unit": "video" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 2, "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-first-last-frame", "native_audio": { "default": true, "source_ids": [ "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "gemini-guide" ], "state": "supported" }, { "max_count": 1, "media_type": "image", "min_count": 1, "role": "end_image", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-guide" ], "task": "first_last_frame_to_video" }, { "api_mode": "veo-3.1-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_adult" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 1, "unit": "video" } ], "duration": { "max": 8, "min": 8, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-reference-to-video", "native_audio": { "default": true, "source_ids": [ "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "max_count": 3, "media_type": "image", "min_count": 1, "role": "asset_reference", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-guide" ], "task": "reference_images_to_video" }, { "api_mode": "veo-3.1-generate-preview", "controls": [ { "max": 20, "min": 1, "mode": "range", "name": "extension_count", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 1, "unit": "extension" }, { "mode": "exact_set", "name": "duration_seconds_request", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "second", "values": [ "8" ] } ], "duration": { "max": 7, "min": 7, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-video-extension", "native_audio": { "default": true, "source_ids": [ "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "generated_by=veo", "resolution=720p", "aspect_ratio=16:9_or_9:16" ], "duration_unit": "second", "formats": [ "mp4" ], "max_count": 1, "max_duration": 141, "media_type": "video", "min_count": 1, "role": "start_video", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-guide" ], "task": "video_extension" }, { "api_mode": "veo-3.1-generate-001", "controls": [ { "max": 4, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "agent-model" ], "state": "supported", "step": 1, "unit": "video" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "agent-model" ], "state": "supported", "step": 2, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "agent-model" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "agent-text-to-video", "native_audio": { "source_ids": [ "agent-model" ], "state": "unsupported" }, "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "source_ids": [ "agent-model" ] } ], "source_ids": [ "agent-model" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "agent-model" ], "task": "text_to_video" }, { "api_mode": "veo-3.1-generate-001", "controls": [ { "max": 4, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "agent-model" ], "state": "supported", "step": 1, "unit": "video" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "agent-model" ], "state": "supported", "step": 2, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "agent-model" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "agent-image-to-video", "native_audio": { "source_ids": [ "agent-model" ], "state": "unsupported" }, "reference_inputs": [ { "constraints": [ "file_size_less_than_or_equal_to=20MB" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "agent-model" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "source_ids": [ "agent-model" ] } ], "source_ids": [ "agent-model" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "agent-model" ], "task": "image_to_video" } ], "conflicts": [ { "handling": "Keep model-level status unknown and preserve separate Gemini Developer and Agent Platform profiles and identifiers.", "path": "model.status,api_identifiers,capability_profiles.*.controls.output_count", "source_ids": [ "gemini-model", "gemini-guide", "agent-model", "gemini-changelog" ], "summary": "Gemini Developer publishes a Preview identifier and one output per request, while Agent Platform publishes a GA -001 identifier and up to four outputs." }, { "handling": "Keep native-audio state scoped to each service profile and retain both audio and silent Agent Platform charges without treating either as a universal model behavior.", "path": "capability_profiles.*.native_audio", "source_ids": [ "gemini-model", "gemini-guide", "agent-model", "agent-pricing" ], "summary": "Gemini Developer says native audio is always on, while the Agent Platform model table says sound generation is unsupported and its pricing page nevertheless lists audio rates." }, { "handling": "Record extension only in the Gemini Developer service profile, where its input and duration constraints are explicit; do not infer general Agent Platform video input.", "path": "capability_profiles.*.reference_inputs.start_video", "source_ids": [ "agent-model", "gemini-guide" ], "summary": "The Agent Platform modality table says video input is unsupported while also listing video extension as supported." }, { "handling": "Scope every charge by service and audio condition; pricing remains partial pending reconciliation of the Agent Platform surfaces.", "path": "pricing.charges.*", "source_ids": [ "gemini-pricing", "agent-model", "agent-pricing" ], "summary": "Gemini Developer exposes native-audio generation only, while Agent Platform publishes both audio and silent rates despite its model page saying sound generation is unsupported." } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "English" } ], "listed_count": 1, "published_label": "English is fully supported; other languages have not been evaluated.", "scope": "prompt_input", "source_ids": [ "gemini-guide" ], "state": "supported" }, "limitations": [ { "id": "request-latency", "source_ids": [ "gemini-guide" ], "summary": "Google documents request latency ranging from eleven seconds to six minutes during peak hours." }, { "id": "language-evaluation", "source_ids": [ "gemini-guide" ], "summary": "English is fully supported; other languages have not been evaluated." }, { "id": "asset-retention", "source_ids": [ "gemini-guide" ], "summary": "Generated videos are retained for two days; using a video in another request resets the retention timer." }, { "id": "audio-processing-failures", "source_ids": [ "gemini-guide" ], "summary": "Audio processing failures can prevent video generation; failed generations are not charged." }, { "id": "multiple-video-prompting", "source_ids": [ "gemini-guide" ], "summary": "Multiple-video prompting is not supported." } ], "model": { "id": "google/veo-3-1", "lab": "Google", "modality": "video", "name": "Veo 3.1", "source_ids": [ "deepmind-overview", "gemini-model", "agent-model" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 0.4, "applies_when": [ "service=gemini_developer", "native_audio=true", "size=720p_or_1080p" ], "denomination": "USD", "id": "gemini-audio-720p-1080p", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.6, "applies_when": [ "service=gemini_developer", "native_audio=true", "size=4k" ], "denomination": "USD", "id": "gemini-audio-4k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.4, "applies_when": [ "service=agent_platform", "native_audio=true", "size=720p_or_1080p" ], "denomination": "USD", "id": "agent-audio-720p-1080p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.6, "applies_when": [ "service=agent_platform", "native_audio=true", "size=4k" ], "denomination": "USD", "id": "agent-audio-4k", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.2, "applies_when": [ "service=agent_platform", "native_audio=false", "size=720p_or_1080p" ], "denomination": "USD", "id": "agent-silent-720p-1080p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.4, "applies_when": [ "service=agent_platform", "native_audio=false", "size=4k" ], "denomination": "USD", "id": "agent-silent-4k", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" } ], "source_ids": [ "gemini-pricing", "agent-pricing" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "deepmind-overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://deepmind.google/models/veo/" }, { "id": "gemini-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/models/veo-3.1-generate-preview" }, { "id": "gemini-guide", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/veo" }, { "id": "gemini-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "gemini-changelog", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/changelog" }, { "id": "agent-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate" }, { "id": "agent-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "gemini-model", "gemini-guide" ], "value": "veo-3.1-fast-generate-preview" }, { "kind": "model_id", "source_ids": [ "agent-model" ], "value": "veo-3.1-fast-generate-001" } ], "capability_profiles": [ { "api_mode": "veo-3.1-fast-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_all" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 1, "unit": "video" } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "gemini-mp4", "source_ids": [ "gemini-guide" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 2, "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-fast-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-text-to-video", "native_audio": { "default": true, "source_ids": [ "gemini-model", "gemini-guide" ], "state": "supported" }, "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-model", "gemini-guide" ], "task": "text_to_video" }, { "api_mode": "veo-3.1-fast-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_adult" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 1, "unit": "video" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 2, "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-fast-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-image-to-video", "native_audio": { "default": true, "source_ids": [ "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-guide" ], "task": "image_to_video" }, { "api_mode": "veo-3.1-fast-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_adult" ] } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 2, "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-fast-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-first-last-frame", "native_audio": { "default": true, "source_ids": [ "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "gemini-guide" ], "state": "supported" }, { "max_count": 1, "media_type": "image", "min_count": 1, "role": "end_image", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-guide" ], "task": "first_last_frame_to_video" }, { "api_mode": "veo-3.1-fast-generate-preview", "controls": [ { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_adult" ] } ], "duration": { "max": 8, "min": 8, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-fast-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-reference-to-video", "native_audio": { "default": true, "source_ids": [ "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "max_count": 3, "media_type": "image", "min_count": 1, "role": "asset_reference", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "4k", "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-guide" ], "task": "reference_images_to_video" }, { "api_mode": "veo-3.1-fast-generate-preview", "controls": [ { "max": 20, "min": 1, "mode": "range", "name": "extension_count", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 1, "unit": "extension" }, { "mode": "exact_set", "name": "duration_seconds_request", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "second", "values": [ "8" ] } ], "duration": { "max": 7, "min": 7, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-fast-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-video-extension", "native_audio": { "default": true, "source_ids": [ "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "generated_by=veo", "resolution=720p", "aspect_ratio=16:9_or_9:16" ], "duration_unit": "second", "formats": [ "mp4" ], "max_count": 1, "max_duration": 141, "media_type": "video", "min_count": 1, "role": "start_video", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-guide" ], "task": "video_extension" }, { "api_mode": "veo-3.1-fast-generate-001", "controls": [ { "max": 4, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "agent-model" ], "state": "supported", "step": 1, "unit": "video" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "agent-model" ], "state": "supported", "step": 2, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "agent-model" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "agent-text-to-video", "native_audio": { "source_ids": [ "agent-model" ], "state": "unsupported" }, "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "source_ids": [ "agent-model" ] } ], "source_ids": [ "agent-model" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "agent-model" ], "task": "text_to_video" }, { "api_mode": "veo-3.1-fast-generate-001", "controls": [ { "max": 4, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "agent-model" ], "state": "supported", "step": 1, "unit": "video" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "agent-model" ], "state": "supported", "step": 2, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "agent-model" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "agent-image-to-video", "native_audio": { "source_ids": [ "agent-model" ], "state": "unsupported" }, "reference_inputs": [ { "constraints": [ "file_size_less_than_or_equal_to=20MB" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "agent-model" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "source_ids": [ "agent-model" ] } ], "source_ids": [ "agent-model" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "agent-model" ], "task": "image_to_video" } ], "conflicts": [ { "handling": "Keep model-level status unknown and preserve separate Gemini Developer and Agent Platform profiles and identifiers.", "path": "model.status,api_identifiers,capability_profiles.*.controls.output_count", "source_ids": [ "gemini-model", "gemini-guide", "agent-model", "gemini-changelog" ], "summary": "Gemini Developer publishes a Preview identifier and one output per request, while Agent Platform publishes a GA -001 identifier and up to four outputs." }, { "handling": "Keep native-audio state scoped to each service profile and retain both audio and silent Agent Platform charges without treating either as a universal model behavior.", "path": "capability_profiles.*.native_audio", "source_ids": [ "gemini-model", "gemini-guide", "agent-model", "agent-pricing" ], "summary": "Gemini Developer says native audio is always on, while the Agent Platform model table says sound generation is unsupported and its pricing page nevertheless lists audio rates." }, { "handling": "Omit 4K from Agent capability profiles, retain the explicitly published Agent 4K charges, and keep Gemini 4K in its separate service profiles.", "path": "capability_profiles.agent-*.size.options,pricing.charges.agent-*-4k", "source_ids": [ "gemini-guide", "agent-model", "agent-pricing" ], "summary": "The Agent Platform model table lists Fast output only at 720p and 1080p, while Agent pricing publishes Fast 4K audio and silent rates and Gemini Developer documents 4K output." }, { "handling": "Record extension only in the Gemini Developer profile, where its input and duration constraints are explicit.", "path": "capability_profiles.*.reference_inputs.start_video", "source_ids": [ "agent-model", "gemini-guide" ], "summary": "The Agent Platform modality table says video input is unsupported while also listing video extension as supported." } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "English" } ], "listed_count": 1, "published_label": "English is fully supported; other languages have not been evaluated.", "scope": "prompt_input", "source_ids": [ "gemini-guide" ], "state": "supported" }, "limitations": [ { "id": "request-latency", "source_ids": [ "gemini-guide" ], "summary": "Google documents request latency ranging from eleven seconds to six minutes during peak hours." }, { "id": "language-evaluation", "source_ids": [ "gemini-guide" ], "summary": "English is fully supported; other languages have not been evaluated." }, { "id": "asset-retention", "source_ids": [ "gemini-guide" ], "summary": "Generated videos are retained for two days; using a video in another request resets the retention timer." }, { "id": "audio-processing-failures", "source_ids": [ "gemini-guide" ], "summary": "Audio processing failures can prevent video generation; failed generations are not charged." }, { "id": "multiple-video-prompting", "source_ids": [ "gemini-guide" ], "summary": "Multiple-video prompting is not supported." } ], "model": { "id": "google/veo-3-1-fast", "lab": "Google", "modality": "video", "name": "Veo 3.1 Fast", "source_ids": [ "deepmind-overview", "gemini-model", "agent-model" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 0.1, "applies_when": [ "service=gemini_developer", "native_audio=true", "size=720p" ], "denomination": "USD", "id": "gemini-audio-720p", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.12, "applies_when": [ "service=gemini_developer", "native_audio=true", "size=1080p" ], "denomination": "USD", "id": "gemini-audio-1080p", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.3, "applies_when": [ "service=gemini_developer", "native_audio=true", "size=4k" ], "denomination": "USD", "id": "gemini-audio-4k", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.1, "applies_when": [ "service=agent_platform", "native_audio=true", "size=720p" ], "denomination": "USD", "id": "agent-audio-720p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.12, "applies_when": [ "service=agent_platform", "native_audio=true", "size=1080p" ], "denomination": "USD", "id": "agent-audio-1080p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.3, "applies_when": [ "service=agent_platform", "native_audio=true", "size=4k" ], "denomination": "USD", "id": "agent-audio-4k", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.08, "applies_when": [ "service=agent_platform", "native_audio=false", "size=720p" ], "denomination": "USD", "id": "agent-silent-720p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.1, "applies_when": [ "service=agent_platform", "native_audio=false", "size=1080p" ], "denomination": "USD", "id": "agent-silent-1080p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.25, "applies_when": [ "service=agent_platform", "native_audio=false", "size=4k" ], "denomination": "USD", "id": "agent-silent-4k", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" } ], "source_ids": [ "gemini-pricing", "agent-pricing" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "deepmind-overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://deepmind.google/models/veo/" }, { "id": "gemini-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/models/veo-3.1-generate-preview" }, { "id": "gemini-guide", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/veo" }, { "id": "gemini-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "gemini-changelog", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://ai.google.dev/gemini-api/docs/changelog" }, { "id": "agent-model", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate" }, { "id": "agent-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "gemini-model", "gemini-guide", "gemini-changelog" ], "value": "veo-3.1-lite-generate-preview" }, { "kind": "model_id", "source_ids": [ "agent-model" ], "value": "veo-3.1-lite-generate-001" } ], "capability_profiles": [ { "api_mode": "veo-3.1-lite-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_all" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "gemini-model", "gemini-guide" ], "state": "supported", "step": 1, "unit": "video" } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "gemini-mp4", "source_ids": [ "gemini-guide" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 2, "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-lite-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-text-to-video", "native_audio": { "default": true, "source_ids": [ "gemini-model", "gemini-guide" ], "state": "supported" }, "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-model", "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-model", "gemini-guide" ], "task": "text_to_video" }, { "api_mode": "veo-3.1-lite-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_adult" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "gemini-model", "gemini-guide" ], "state": "supported", "step": 1, "unit": "video" } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "gemini-mp4", "source_ids": [ "gemini-guide" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 2, "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-lite-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-image-to-video", "native_audio": { "default": true, "source_ids": [ "gemini-model", "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-model", "gemini-guide" ], "task": "image_to_video" }, { "api_mode": "veo-3.1-lite-generate-preview", "controls": [ { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "16:9", "9:16" ] }, { "mode": "exact_set", "name": "person_generation", "source_ids": [ "gemini-guide" ], "state": "supported", "values": [ "allow_adult" ] }, { "default": 1, "max": 1, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "gemini-model", "gemini-guide" ], "state": "supported", "step": 1, "unit": "video" } ], "delivery_profiles": [ { "default_format": "mp4", "formats": [ "mp4" ], "id": "gemini-mp4", "source_ids": [ "gemini-guide" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "gemini-guide" ], "state": "supported", "step": 2, "unit": "second" }, "endpoint": "POST https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-lite-generate-preview:predictLongRunning", "frame_rate": { "mode": "exact_set", "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "gemini-first-last-frame", "native_audio": { "default": true, "source_ids": [ "gemini-guide" ], "state": "supported" }, "reference_inputs": [ { "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "gemini-guide" ], "state": "supported" }, { "max_count": 1, "media_type": "image", "min_count": 1, "role": "end_image", "source_ids": [ "gemini-guide" ], "state": "supported" } ], "size": { "default": "720p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "gemini-guide" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "render_modes": [ "duration=8_seconds" ], "source_ids": [ "gemini-guide" ] } ], "source_ids": [ "gemini-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "gemini-guide" ], "task": "first_last_frame_to_video" }, { "api_mode": "veo-3.1-lite-generate-001", "controls": [ { "max": 4, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "agent-model" ], "state": "supported", "step": 1, "unit": "video" } ], "delivery_profiles": [ { "formats": [ "mp4" ], "id": "agent-mp4", "source_ids": [ "agent-model" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "agent-model" ], "state": "supported", "step": 2, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "agent-model" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "agent-text-to-video", "native_audio": { "source_ids": [ "agent-model" ], "state": "supported" }, "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "source_ids": [ "agent-model" ] } ], "source_ids": [ "agent-model" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "agent-model" ], "task": "text_to_video" }, { "api_mode": "veo-3.1-lite-generate-001", "controls": [ { "max": 4, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "agent-model" ], "state": "supported", "step": 1, "unit": "video" } ], "delivery_profiles": [ { "formats": [ "mp4" ], "id": "agent-mp4", "source_ids": [ "agent-model" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "agent-model" ], "state": "supported", "step": 2, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "agent-model" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "agent-image-to-video", "native_audio": { "source_ids": [ "agent-model" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "file_size_less_than_or_equal_to=20MB", "input_resolution=720p_or_1080p" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "agent-model" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "source_ids": [ "agent-model" ] } ], "source_ids": [ "agent-model" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "agent-model" ], "task": "image_to_video" }, { "api_mode": "veo-3.1-lite-generate-001", "controls": [ { "max": 4, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "agent-model" ], "state": "supported", "step": 1, "unit": "video" } ], "delivery_profiles": [ { "formats": [ "mp4" ], "id": "agent-mp4", "source_ids": [ "agent-model" ], "state": "supported", "transport": "long_running_operation" } ], "duration": { "max": 8, "min": 4, "mode": "range", "source_ids": [ "agent-model" ], "state": "supported", "step": 2, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "agent-model" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "agent-first-last-frame", "native_audio": { "source_ids": [ "agent-model" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "file_size_less_than_or_equal_to=20MB", "input_resolution=720p_or_1080p" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "agent-model" ], "state": "supported" }, { "constraints": [ "file_size_less_than_or_equal_to=20MB", "input_resolution=720p_or_1080p" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "end_image", "source_ids": [ "agent-model" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9", "9:16" ], "id": "720p", "source_ids": [ "agent-model" ] }, { "aspect_ratios": [ "16:9", "9:16" ], "id": "1080p", "source_ids": [ "agent-model" ] } ], "source_ids": [ "agent-model" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "agent-model" ], "task": "first_last_frame_to_video" } ], "conflicts": [ { "handling": "Preserve separate service identifiers and capability profiles rather than selecting one service contract as universal.", "path": "api_identifiers,capability_profiles.*.controls.output_count", "source_ids": [ "gemini-model", "gemini-guide", "agent-model" ], "summary": "Gemini Developer publishes a Preview identifier and one output per request, while Agent Platform publishes a -001 identifier and up to four outputs." }, { "handling": "Do not record an extension profile until Google publishes a consistent callable contract for the Lite model.", "path": "capability_profiles.video_extension", "source_ids": [ "gemini-model", "gemini-guide", "agent-model" ], "summary": "The Gemini model page and guide say Veo 3.1 Lite does not support extension, while the Agent Platform model table labels extension supported even though that same table marks video input unsupported." }, { "handling": "Keep the always-on default only on Gemini Developer profiles and omit a default on Agent Platform profiles.", "path": "capability_profiles.*.native_audio", "source_ids": [ "gemini-guide", "agent-model", "agent-pricing" ], "summary": "Gemini Developer says native audio is always on, while Agent Platform says sound generation is supported and publishes both audio and silent rates without documenting a default." }, { "handling": "Retain the published rate card as pricing metadata without implying that pay-as-you-go access is available.", "path": "pricing.charges.*", "source_ids": [ "agent-model", "agent-pricing" ], "summary": "Agent Platform publishes per-second Lite rates while its model page says pay-as-you-go is not supported and fixed quota is supported." } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "English" } ], "listed_count": 1, "published_label": "English is fully supported; other languages have not been evaluated.", "scope": "prompt_input", "source_ids": [ "gemini-guide" ], "state": "supported" }, "limitations": [ { "id": "request-latency", "source_ids": [ "gemini-guide" ], "summary": "Google documents request latency ranging from eleven seconds to six minutes during peak hours." }, { "id": "language-evaluation", "source_ids": [ "gemini-guide" ], "summary": "English is fully supported; other languages have not been evaluated." }, { "id": "asset-retention", "source_ids": [ "gemini-guide" ], "summary": "Generated videos are retained for two days and must be downloaded before removal." }, { "id": "audio-processing-failures", "source_ids": [ "gemini-guide", "gemini-pricing" ], "summary": "Audio processing or safety issues can prevent video generation; blocked generations are not charged." } ], "model": { "id": "google/veo-3-1-lite", "lab": "Google", "modality": "video", "name": "Veo 3.1 Lite", "source_ids": [ "gemini-model", "gemini-guide", "gemini-changelog", "agent-model", "cloud-release" ], "status": "preview" }, "pricing": { "charges": [ { "amount": 0.05, "applies_when": [ "service=gemini_developer", "native_audio=true", "size=720p" ], "denomination": "USD", "id": "gemini-audio-720p", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.08, "applies_when": [ "service=gemini_developer", "native_audio=true", "size=1080p" ], "denomination": "USD", "id": "gemini-audio-1080p", "kind": "metered", "per": 1, "source_ids": [ "gemini-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.05, "applies_when": [ "service=agent_platform", "native_audio=true", "size=720p" ], "denomination": "USD", "id": "agent-audio-720p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.08, "applies_when": [ "service=agent_platform", "native_audio=true", "size=1080p" ], "denomination": "USD", "id": "agent-audio-1080p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.03, "applies_when": [ "service=agent_platform", "native_audio=false", "size=720p" ], "denomination": "USD", "id": "agent-silent-720p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.05, "applies_when": [ "service=agent_platform", "native_audio=false", "size=1080p" ], "denomination": "USD", "id": "agent-silent-1080p", "kind": "metered", "per": 1, "source_ids": [ "agent-pricing" ], "state": "known", "unit": "output_second" } ], "source_ids": [ "gemini-pricing", "agent-pricing" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "gemini-model", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/models/veo-3.1-lite-generate-preview" }, { "id": "gemini-guide", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/veo" }, { "id": "gemini-pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/pricing" }, { "id": "gemini-changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://ai.google.dev/gemini-api/docs/changelog" }, { "id": "agent-model", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/veo/3-1-generate" }, { "id": "agent-pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, { "id": "cloud-release", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://cloud.google.com/blog/products/ai-machine-learning/veo-3-1-lite-and-a-new-veo-upscaling-capability-on-vertex-ai" } ], "verification": { "state": "unverified" } }, { "capability_profiles": [ { "controls": [ { "mode": "exact_set", "name": "prompt_input_mode", "source_ids": [ "generate-api" ], "state": "supported", "values": [ "text_prompt" ] }, { "max": 2147483647, "min": 0, "mode": "range", "name": "request_seed", "source_ids": [ "generate-api" ], "state": "supported", "step": 1 }, { "default": "DEFAULT", "mode": "exact_set", "name": "rendering_speed", "source_ids": [ "generate-api" ], "state": "supported", "values": [ "FLASH", "TURBO", "DEFAULT", "QUALITY" ] }, { "mode": "exact_set", "name": "magic_prompt", "source_ids": [ "generate-api" ], "state": "supported", "values": [ "AUTO", "ON", "OFF" ] }, { "default": 1, "max": 8, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "generate-api" ], "state": "supported", "step": 1 }, { "default": "GENERAL", "mode": "exact_set", "name": "style_type", "source_ids": [ "generate-api" ], "state": "supported", "values": [ "AUTO", "GENERAL", "REALISTIC", "DESIGN", "FICTION" ] }, { "mode": "exact_set", "name": "enable_copyright_detection", "source_ids": [ "generate-api" ], "state": "supported", "values": [ "false", "true" ] } ], "delivery_profiles": [ { "endpoint": "POST /v1/ideogram-v3/generate", "id": "synchronous-temporary-url", "source_ids": [ "generate-api" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "generate-api" ], "state": "not_applicable" }, "endpoint": "POST /v1/ideogram-v3/generate", "frame_rate": { "source_ids": [ "generate-api" ], "state": "not_applicable" }, "id": "image-generation", "native_audio": { "source_ids": [ "generate-api" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "aggregate_max_file_size=10 MB" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 3, "media_type": "image", "min_count": 0, "role": "style_reference", "source_ids": [ "model-page", "generate-api" ], "state": "supported" }, { "constraints": [ "aggregate_max_file_size=10 MB" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 0, "role": "character_reference", "source_ids": [ "generate-api" ], "state": "supported" }, { "constraints": [ "count_must_match_character_reference_images=true", "image_mode=grayscale", "dimensions_must_match_corresponding_character_reference=true" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image_mask", "min_count": 0, "role": "character_reference_mask", "source_ids": [ "generate-api" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "id": "512x1536", "source_ids": [ "generate-api" ] }, { "id": "576x1408", "source_ids": [ "generate-api" ] }, { "id": "576x1472", "source_ids": [ "generate-api" ] }, { "id": "576x1536", "source_ids": [ "generate-api" ] }, { "id": "640x1344", "source_ids": [ "generate-api" ] }, { "id": "640x1408", "source_ids": [ "generate-api" ] }, { "id": "640x1472", "source_ids": [ "generate-api" ] }, { "id": "640x1536", "source_ids": [ "generate-api" ] }, { "id": "704x1152", "source_ids": [ "generate-api" ] }, { "id": "704x1216", "source_ids": [ "generate-api" ] }, { "id": "704x1280", "source_ids": [ "generate-api" ] }, { "id": "704x1344", "source_ids": [ "generate-api" ] }, { "id": "704x1408", "source_ids": [ "generate-api" ] }, { "id": "704x1472", "source_ids": [ "generate-api" ] }, { "id": "736x1312", "source_ids": [ "generate-api" ] }, { "id": "768x1088", "source_ids": [ "generate-api" ] }, { "id": "768x1216", "source_ids": [ "generate-api" ] }, { "id": "768x1280", "source_ids": [ "generate-api" ] }, { "id": "768x1344", "source_ids": [ "generate-api" ] }, { "id": "800x1280", "source_ids": [ "generate-api" ] }, { "id": "832x960", "source_ids": [ "generate-api" ] }, { "id": "832x1024", "source_ids": [ "generate-api" ] }, { "id": "832x1088", "source_ids": [ "generate-api" ] }, { "id": "832x1152", "source_ids": [ "generate-api" ] }, { "id": "832x1216", "source_ids": [ "generate-api" ] }, { "id": "832x1248", "source_ids": [ "generate-api" ] }, { "id": "864x1152", "source_ids": [ "generate-api" ] }, { "id": "896x960", "source_ids": [ "generate-api" ] }, { "id": "896x1024", "source_ids": [ "generate-api" ] }, { "id": "896x1088", "source_ids": [ "generate-api" ] }, { "id": "896x1120", "source_ids": [ "generate-api" ] }, { "id": "896x1152", "source_ids": [ "generate-api" ] }, { "id": "960x832", "source_ids": [ "generate-api" ] }, { "id": "960x896", "source_ids": [ "generate-api" ] }, { "id": "960x1024", "source_ids": [ "generate-api" ] }, { "id": "960x1088", "source_ids": [ "generate-api" ] }, { "id": "1024x832", "source_ids": [ "generate-api" ] }, { "id": "1024x896", "source_ids": [ "generate-api" ] }, { "id": "1024x960", "source_ids": [ "generate-api" ] }, { "id": "1024x1024", "source_ids": [ "generate-api" ] }, { "id": "1088x768", "source_ids": [ "generate-api" ] }, { "id": "1088x832", "source_ids": [ "generate-api" ] }, { "id": "1088x896", "source_ids": [ "generate-api" ] }, { "id": "1088x960", "source_ids": [ "generate-api" ] }, { "id": "1120x896", "source_ids": [ "generate-api" ] }, { "id": "1152x704", "source_ids": [ "generate-api" ] }, { "id": "1152x832", "source_ids": [ "generate-api" ] }, { "id": "1152x864", "source_ids": [ "generate-api" ] }, { "id": "1152x896", "source_ids": [ "generate-api" ] }, { "id": "1216x704", "source_ids": [ "generate-api" ] }, { "id": "1216x768", "source_ids": [ "generate-api" ] }, { "id": "1216x832", "source_ids": [ "generate-api" ] }, { "id": "1248x832", "source_ids": [ "generate-api" ] }, { "id": "1280x704", "source_ids": [ "generate-api" ] }, { "id": "1280x768", "source_ids": [ "generate-api" ] }, { "id": "1280x800", "source_ids": [ "generate-api" ] }, { "id": "1312x736", "source_ids": [ "generate-api" ] }, { "id": "1344x640", "source_ids": [ "generate-api" ] }, { "id": "1344x704", "source_ids": [ "generate-api" ] }, { "id": "1344x768", "source_ids": [ "generate-api" ] }, { "id": "1408x576", "source_ids": [ "generate-api" ] }, { "id": "1408x640", "source_ids": [ "generate-api" ] }, { "id": "1408x704", "source_ids": [ "generate-api" ] }, { "id": "1472x576", "source_ids": [ "generate-api" ] }, { "id": "1472x640", "source_ids": [ "generate-api" ] }, { "id": "1472x704", "source_ids": [ "generate-api" ] }, { "id": "1536x512", "source_ids": [ "generate-api" ] }, { "id": "1536x576", "source_ids": [ "generate-api" ] }, { "id": "1536x640", "source_ids": [ "generate-api" ] } ], "source_ids": [ "generate-api" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "generate-api" ], "task": "text_to_image", "text_input": { "source_ids": [ "generate-api" ], "state": "unknown" } } ], "documentation_state": "documented", "limitations": [ { "id": "temporary-hosted-output-links", "source_ids": [ "generate-api" ], "summary": "Ideogram says generated image links remain available only for a limited period and must be downloaded for durable storage." } ], "model": { "id": "ideogram/ideogram-3-0", "lab": "Ideogram", "modality": "image", "name": "Ideogram 3.0", "source_ids": [ "model-page", "generate-api" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 0.03, "applies_when": [ "rendering_speed=FLASH", "character_reference_images=absent" ], "denomination": "USD", "id": "text-to-image-flash", "kind": "metered", "per": 1, "profile_id": "image-generation", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.03, "applies_when": [ "rendering_speed=TURBO", "character_reference_images=absent" ], "denomination": "USD", "id": "text-to-image-turbo", "kind": "metered", "per": 1, "profile_id": "image-generation", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.06, "applies_when": [ "rendering_speed=DEFAULT", "character_reference_images=absent" ], "denomination": "USD", "id": "text-to-image-default", "kind": "metered", "per": 1, "profile_id": "image-generation", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.09, "applies_when": [ "rendering_speed=QUALITY", "character_reference_images=absent" ], "denomination": "USD", "id": "text-to-image-quality", "kind": "metered", "per": 1, "profile_id": "image-generation", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "applies_when": [ "rendering_speed=FLASH", "character_reference_images=present" ], "id": "character-reference-flash", "profile_id": "image-generation", "qualifier": "The pricing table lists no Flash rate for generations using Character Reference.", "source_ids": [ "pricing" ], "state": "unknown" }, { "amount": 0.1, "applies_when": [ "rendering_speed=TURBO", "character_reference_images=present" ], "denomination": "USD", "id": "character-reference-turbo", "kind": "metered", "per": 1, "profile_id": "image-generation", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.15, "applies_when": [ "rendering_speed=DEFAULT", "character_reference_images=present" ], "denomination": "USD", "id": "character-reference-default", "kind": "metered", "per": 1, "profile_id": "image-generation", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.2, "applies_when": [ "rendering_speed=QUALITY", "character_reference_images=present" ], "denomination": "USD", "id": "character-reference-quality", "kind": "metered", "per": 1, "profile_id": "image-generation", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" } ], "source_ids": [ "pricing" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://ideogram.ai/models/3.0/" }, { "id": "generate-api", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://developer.ideogram.ai/api-reference/api-reference/generate-v3" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://ideogram.ai/api-pricing/" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "nf4-model-card", "open-repository" ], "value": "ideogram-ai/ideogram-4-nf4" }, { "kind": "model_id", "source_ids": [ "fp8-model-card", "open-repository" ], "value": "ideogram-ai/ideogram-4-fp8" }, { "kind": "model_id", "source_ids": [ "diffusers-model-card", "open-repository" ], "value": "ideogram-ai/ideogram-4-nf4-diffusers" } ], "capability_profiles": [ { "controls": [ { "mode": "exact_set", "name": "prompt_input_mode", "source_ids": [ "generate-api" ], "state": "supported", "values": [ "text_prompt", "json_prompt" ] }, { "default": "DEFAULT", "mode": "exact_set", "name": "rendering_speed", "source_ids": [ "generate-api", "pricing" ], "state": "supported", "unsupported_values": [ "FLASH" ], "values": [ "TURBO", "DEFAULT", "QUALITY" ] }, { "mode": "exact_set", "name": "enable_copyright_detection", "source_ids": [ "generate-api" ], "state": "supported", "values": [ "false", "true" ] }, { "mode": "exact_set", "name": "structured_element_type", "source_ids": [ "generate-api" ], "state": "supported", "values": [ "obj", "text" ] }, { "max": 1000, "min": 0, "mode": "range", "name": "bounding_box_coordinate", "source_ids": [ "generate-api" ], "state": "supported", "step": 1, "unit": "normalized_coordinate" }, { "name": "output_count", "source_ids": [ "generate-api" ], "state": "unknown" }, { "name": "request_seed", "source_ids": [ "generate-api" ], "state": "unknown" }, { "name": "output_format", "source_ids": [ "generate-api" ], "state": "unknown" } ], "delivery_profiles": [ { "endpoint": "POST /v1/ideogram-v4/generate", "id": "synchronous-temporary-url", "source_ids": [ "generate-api" ], "state": "supported", "transport": "temporary_url" }, { "endpoint": "POST /v1/ideogram-v4/async/generate", "id": "asynchronous-submission", "source_ids": [ "generate-async-api" ], "state": "supported", "transport": "asynchronous_job" }, { "endpoint": "GET /v1/generations/{generation_id}", "id": "asynchronous-polling", "source_ids": [ "generate-async-api" ], "state": "supported", "transport": "polling" }, { "endpoint": "POST {webhook_url}", "id": "asynchronous-webhook", "source_ids": [ "generate-async-api", "webhooks-guide" ], "state": "supported", "transport": "webhook" } ], "duration": { "source_ids": [ "model-page", "release-announcement" ], "state": "not_applicable" }, "endpoint": "POST /v1/ideogram-v4/generate", "frame_rate": { "source_ids": [ "model-page", "release-announcement" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page", "release-announcement" ], "state": "not_applicable" }, "size": { "mode": "exact_set", "options": [ { "id": "2048x2048", "source_ids": [ "generate-api" ] }, { "id": "1440x2880", "source_ids": [ "generate-api" ] }, { "id": "2880x1440", "source_ids": [ "generate-api" ] }, { "id": "1664x2496", "source_ids": [ "generate-api" ] }, { "id": "2496x1664", "source_ids": [ "generate-api" ] }, { "id": "1792x2240", "source_ids": [ "generate-api" ] }, { "id": "2240x1792", "source_ids": [ "generate-api" ] }, { "id": "1440x2560", "source_ids": [ "generate-api" ] }, { "id": "2560x1440", "source_ids": [ "generate-api" ] }, { "id": "1600x2560", "source_ids": [ "generate-api" ] }, { "id": "2560x1600", "source_ids": [ "generate-api" ] }, { "id": "1728x2304", "source_ids": [ "generate-api" ] }, { "id": "2304x1728", "source_ids": [ "generate-api" ] }, { "id": "1296x3168", "source_ids": [ "generate-api" ] }, { "id": "3168x1296", "source_ids": [ "generate-api" ] }, { "id": "1152x2944", "source_ids": [ "generate-api" ] }, { "id": "2944x1152", "source_ids": [ "generate-api" ] }, { "id": "1248x3328", "source_ids": [ "generate-api" ] }, { "id": "3328x1248", "source_ids": [ "generate-api" ] }, { "id": "1280x3072", "source_ids": [ "generate-api" ] }, { "id": "3072x1280", "source_ids": [ "generate-api" ] }, { "id": "1024x3072", "source_ids": [ "generate-api" ] }, { "id": "3072x1024", "source_ids": [ "generate-api" ] }, { "id": "1024x1024", "source_ids": [ "generate-api" ] }, { "id": "896x1120", "source_ids": [ "generate-api" ] }, { "id": "1120x896", "source_ids": [ "generate-api" ] }, { "id": "864x1152", "source_ids": [ "generate-api" ] }, { "id": "1152x864", "source_ids": [ "generate-api" ] }, { "id": "832x1248", "source_ids": [ "generate-api" ] }, { "id": "1248x832", "source_ids": [ "generate-api" ] }, { "id": "800x1280", "source_ids": [ "generate-api" ] }, { "id": "1280x800", "source_ids": [ "generate-api" ] }, { "id": "720x1280", "source_ids": [ "generate-api" ] }, { "id": "1280x720", "source_ids": [ "generate-api" ] }, { "id": "720x1440", "source_ids": [ "generate-api" ] }, { "id": "1440x720", "source_ids": [ "generate-api" ] }, { "id": "512x1536", "source_ids": [ "generate-api" ] }, { "id": "1536x512", "source_ids": [ "generate-api" ] } ], "source_ids": [ "generate-api" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "generate-api", "generate-async-api" ], "task": "text_to_image", "text_input": { "source_ids": [ "generate-api" ], "state": "unknown" } }, { "controls": [ { "mode": "exact_set", "name": "prompt_input_mode", "source_ids": [ "remix-api" ], "state": "supported", "values": [ "text_prompt" ] }, { "max": 100, "min": 1, "mode": "range", "name": "image_weight", "source_ids": [ "remix-api" ], "state": "supported", "step": 1 }, { "default": "DEFAULT", "mode": "exact_set", "name": "rendering_speed", "source_ids": [ "remix-api" ], "state": "supported", "values": [ "FLASH", "TURBO", "DEFAULT", "QUALITY" ] }, { "mode": "exact_set", "name": "enable_copyright_detection", "source_ids": [ "remix-api" ], "state": "supported", "values": [ "false", "true" ] }, { "name": "output_count", "source_ids": [ "remix-api" ], "state": "unknown" }, { "name": "request_seed", "source_ids": [ "remix-api" ], "state": "unknown" }, { "name": "output_format", "source_ids": [ "remix-api" ], "state": "unknown" } ], "delivery_profiles": [ { "endpoint": "POST /v1/ideogram-v4/remix", "id": "synchronous-temporary-url", "source_ids": [ "remix-api" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "model-page", "release-announcement" ], "state": "not_applicable" }, "endpoint": "POST /v1/ideogram-v4/remix", "frame_rate": { "source_ids": [ "model-page", "release-announcement" ], "state": "not_applicable" }, "id": "image-remix", "native_audio": { "source_ids": [ "model-page", "release-announcement" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "max_file_size=10 MB" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "initial_image", "source_ids": [ "remix-api" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "id": "2048x2048", "source_ids": [ "remix-api" ] }, { "id": "1440x2880", "source_ids": [ "remix-api" ] }, { "id": "2880x1440", "source_ids": [ "remix-api" ] }, { "id": "1664x2496", "source_ids": [ "remix-api" ] }, { "id": "2496x1664", "source_ids": [ "remix-api" ] }, { "id": "1792x2240", "source_ids": [ "remix-api" ] }, { "id": "2240x1792", "source_ids": [ "remix-api" ] }, { "id": "1440x2560", "source_ids": [ "remix-api" ] }, { "id": "2560x1440", "source_ids": [ "remix-api" ] }, { "id": "1600x2560", "source_ids": [ "remix-api" ] }, { "id": "2560x1600", "source_ids": [ "remix-api" ] }, { "id": "1728x2304", "source_ids": [ "remix-api" ] }, { "id": "2304x1728", "source_ids": [ "remix-api" ] }, { "id": "1296x3168", "source_ids": [ "remix-api" ] }, { "id": "3168x1296", "source_ids": [ "remix-api" ] }, { "id": "1152x2944", "source_ids": [ "remix-api" ] }, { "id": "2944x1152", "source_ids": [ "remix-api" ] }, { "id": "1248x3328", "source_ids": [ "remix-api" ] }, { "id": "3328x1248", "source_ids": [ "remix-api" ] }, { "id": "1280x3072", "source_ids": [ "remix-api" ] }, { "id": "3072x1280", "source_ids": [ "remix-api" ] }, { "id": "1024x3072", "source_ids": [ "remix-api" ] }, { "id": "3072x1024", "source_ids": [ "remix-api" ] }, { "id": "1024x1024", "source_ids": [ "remix-api" ] }, { "id": "896x1120", "source_ids": [ "remix-api" ] }, { "id": "1120x896", "source_ids": [ "remix-api" ] }, { "id": "864x1152", "source_ids": [ "remix-api" ] }, { "id": "1152x864", "source_ids": [ "remix-api" ] }, { "id": "832x1248", "source_ids": [ "remix-api" ] }, { "id": "1248x832", "source_ids": [ "remix-api" ] }, { "id": "800x1280", "source_ids": [ "remix-api" ] }, { "id": "1280x800", "source_ids": [ "remix-api" ] }, { "id": "720x1280", "source_ids": [ "remix-api" ] }, { "id": "1280x720", "source_ids": [ "remix-api" ] }, { "id": "720x1440", "source_ids": [ "remix-api" ] }, { "id": "1440x720", "source_ids": [ "remix-api" ] }, { "id": "512x1536", "source_ids": [ "remix-api" ] }, { "id": "1536x512", "source_ids": [ "remix-api" ] } ], "source_ids": [ "remix-api" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "remix-api" ], "task": "image_remix", "text_input": { "source_ids": [ "remix-api" ], "state": "unknown" } }, { "controls": [ { "default": "AUTO", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "magic-prompt-api" ], "state": "supported", "values": [ "AUTO", "1x4", "1x3", "1x2", "9x16", "10x16", "2x3", "3x4", "4x5", "1x1", "5x4", "4x3", "3x2", "16x10", "16x9", "2x1", "3x1", "4x1" ] } ], "delivery_profiles": [ { "endpoint": "POST /v1/ideogram-v4/magic-prompt", "id": "json-response", "source_ids": [ "magic-prompt-api" ], "state": "supported", "transport": "http_response" } ], "duration": { "source_ids": [ "magic-prompt-api" ], "state": "not_applicable" }, "endpoint": "POST /v1/ideogram-v4/magic-prompt", "frame_rate": { "source_ids": [ "magic-prompt-api" ], "state": "not_applicable" }, "id": "magic-prompt", "native_audio": { "source_ids": [ "magic-prompt-api" ], "state": "not_applicable" }, "size": { "source_ids": [ "magic-prompt-api" ], "state": "not_applicable" }, "source_ids": [ "magic-prompt-api" ], "task": "text_to_structured_prompt", "text_input": { "source_ids": [ "magic-prompt-api" ], "state": "unknown" } }, { "controls": [ { "default": "true", "mode": "exact_set", "name": "include_bbox", "source_ids": [ "describe-api" ], "state": "supported", "values": [ "false", "true" ] } ], "delivery_profiles": [ { "endpoint": "POST /v1/ideogram-v4/describe", "id": "json-response", "source_ids": [ "describe-api" ], "state": "supported", "transport": "http_response" } ], "duration": { "source_ids": [ "describe-api" ], "state": "not_applicable" }, "endpoint": "POST /v1/ideogram-v4/describe", "frame_rate": { "source_ids": [ "describe-api" ], "state": "not_applicable" }, "id": "image-to-structured-prompt", "native_audio": { "source_ids": [ "describe-api" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "max_file_size=10 MB" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "describe-api" ], "state": "supported" } ], "size": { "source_ids": [ "describe-api" ], "state": "not_applicable" }, "source_ids": [ "describe-api" ], "task": "image_to_structured_prompt" }, { "controls": [ { "default": "V4_QUALITY_48", "mode": "exact_set", "name": "sampler_preset", "source_ids": [ "open-inference" ], "state": "supported", "values": [ "V4_QUALITY_48", "V4_DEFAULT_20", "V4_TURBO_12" ] }, { "mode": "exact_set", "name": "prompt_input_mode", "source_ids": [ "open-prompting" ], "state": "supported", "unsupported_values": [ "plain_text" ], "values": [ "structured_json" ] }, { "mode": "exact_set", "name": "structured_element_type", "source_ids": [ "open-prompting" ], "state": "supported", "values": [ "obj", "text" ] }, { "max": 1000, "min": 0, "mode": "range", "name": "bounding_box_coordinate", "source_ids": [ "open-prompting" ], "state": "supported", "step": 1, "unit": "normalized_coordinate" }, { "max": 16, "min": 0, "mode": "range", "name": "style_color_palette_count", "source_ids": [ "open-prompting" ], "state": "supported", "step": 1, "unit": "color" }, { "max": 5, "min": 0, "mode": "range", "name": "element_color_palette_count", "source_ids": [ "open-prompting" ], "state": "supported", "step": 1, "unit": "color" } ], "duration": { "source_ids": [ "open-repository" ], "state": "not_applicable" }, "frame_rate": { "source_ids": [ "open-repository" ], "state": "not_applicable" }, "id": "open-weights-text-to-image", "native_audio": { "source_ids": [ "open-repository" ], "state": "not_applicable" }, "size": { "default": "1024x1024", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "open-inference" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "3:2", "height": 1024, "source_ids": [ "open-inference" ], "unit": "pixel", "width": 1536 }, { "aspect_ratio": "2:3", "height": 1536, "source_ids": [ "open-inference" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "~16:9", "height": 1088, "source_ids": [ "open-inference" ], "unit": "pixel", "width": 1920 }, { "aspect_ratio": "~21:9", "height": 768, "source_ids": [ "open-inference" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "~9:16", "height": 1792, "source_ids": [ "open-inference" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "4:1", "height": 400, "source_ids": [ "open-inference" ], "unit": "pixel", "width": 1600 } ], "max_edge": 2048, "max_long_to_short_ratio": 6, "max_total_pixels": 4194304, "min_total_pixels": 65536, "mode": "range", "source_ids": [ "open-inference" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "open-repository", "open-inference", "nf4-model-card", "fp8-model-card", "diffusers-model-card" ], "task": "text_to_image", "text_input": { "source_ids": [ "open-prompting" ], "state": "unknown" }, "variants": [ "ideogram-ai/ideogram-4-nf4", "ideogram-ai/ideogram-4-fp8", "ideogram-ai/ideogram-4-nf4-diffusers" ] } ], "conflicts": [ { "handling": "Record all 38 values from the callable request schema and retain the shorter visible summary as conflicting documentation.", "path": "capability_profiles.text-to-image.size.options", "source_ids": [ "generate-api", "model-page", "release-announcement" ], "summary": "The visible Generate summary refers to 2K output and a collapsed view of 23 choices, while the live embedded request schema enumerates 38 exact 1K and 2K resolutions." }, { "handling": "Mark FLASH unsupported for Generate, retain it as an exposed but unresolved Remix enum value, and leave its Remix price unknown.", "path": "capability_profiles.*.controls.rendering_speed, pricing.charges.*", "source_ids": [ "generate-api", "generate-async-api", "remix-api", "pricing" ], "summary": "Generate explicitly says FLASH is coming soon and currently returns HTTP 400; Remix still exposes FLASH in its enum without that warning, and the pricing table lists no 4.0 Flash rate." }, { "handling": "Record only the V4 Generate and Remix image-output profiles; do not infer V4 Edit, Reframe, or Replace Background endpoints from grouped pricing copy.", "path": "capability_profiles.image-edit, capability_profiles.image-reframe, capability_profiles.replace-background", "source_ids": [ "pricing", "generate-api", "remix-api" ], "summary": "The pricing page groups 4.0 pricing under Generate, Remix, Edit, Reframe and Replace Background, while the developer reference exposes V4 endpoints only for Generate and Remix and labels those other model-specific routes as V3." }, { "handling": "Do not record the marketing pseudo-parameter as a served API identifier; preserve the exact endpoint paths on capability profiles.", "path": "api_identifiers.ideogram-4.0", "source_ids": [ "model-page", "generate-api", "remix-api" ], "summary": "Marketing sample code shows model=ideogram-4.0, while the production API reference selects V4 through endpoint-specific routes and exposes no model request parameter." }, { "handling": "Use the live values as retrieved on 2026-08-10 and retain the stale displayed revision date as provenance.", "path": "pricing.source_revision", "source_ids": [ "pricing", "release-announcement" ], "summary": "The live pricing page displays a last-revised date of August 6, 2025 even though it contains Ideogram 4.0 rates for the model released in June 2026." }, { "handling": "Keep hosted and open-weight prompting rules scoped to their separate profiles and do not imply that the open CaptionVerifier restrictions govern the hosted API.", "path": "capability_profiles.*.controls.color_palette", "source_ids": [ "generate-api", "open-prompting" ], "summary": "The hosted JSON schema accepts six-digit hexadecimal colors in either case, while the open-weight CaptionVerifier guide requires uppercase #RRGGBB values and stricter palette limits." }, { "handling": "Do not treat open-package and production Magic Prompt results as equivalent or derive capability values across them.", "path": "capability_profiles.open-weights-text-to-image.controls.magic_prompt", "source_ids": [ "open-prompting", "magic-prompt-api" ], "summary": "Ideogram says the Magic Prompt shipped with the open package is not the same system used in the production Ideogram product, including when the package calls the Ideogram-hosted ideogram-4-v1 service." } ], "documentation_state": "documented", "limitations": [ { "id": "native-editable-layers-not-yet-available", "source_ids": [ "model-page", "release-announcement" ], "summary": "Ideogram says current 4.0 inference does not yet return alpha channels, editable text layers, or movable image layers directly; those are planned for a follow-up release and currently require separate tools." }, { "id": "open-weights-plain-text-prompts", "source_ids": [ "open-prompting" ], "summary": "Ideogram says passing plain text directly to the open-weight model will not work and will likely trigger a safety warning; a structured JSON prompt or Magic Prompt is required for usable results." }, { "id": "open-weights-runtime-safety-filters", "source_ids": [ "open-safety" ], "summary": "Ideogram says supported open-weight deployments must retain prompt and output NSFW moderation or equivalent stronger filters; disabling runtime screening is not a supported deployment configuration." }, { "id": "temporary-hosted-output-links", "source_ids": [ "generate-api", "remix-api" ], "summary": "Ideogram says hosted Generate and Remix image links remain available only for a limited period and must be downloaded for durable storage." } ], "model": { "aliases": [ "Ideogram 4" ], "id": "ideogram/ideogram-4-0", "lab": "Ideogram", "modality": "image", "name": "Ideogram 4.0", "source_ids": [ "model-page", "release-announcement", "generate-api", "open-repository" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.03, "applies_when": [ "rendering_speed=TURBO" ], "denomination": "USD", "id": "text-to-image-turbo", "kind": "metered", "per": 1, "profile_id": "text-to-image", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.06, "applies_when": [ "rendering_speed=DEFAULT" ], "denomination": "USD", "id": "text-to-image-default", "kind": "metered", "per": 1, "profile_id": "text-to-image", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.1, "applies_when": [ "rendering_speed=QUALITY" ], "denomination": "USD", "id": "text-to-image-quality", "kind": "metered", "per": 1, "profile_id": "text-to-image", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "applies_when": [ "rendering_speed=FLASH" ], "id": "image-remix-flash", "profile_id": "image-remix", "qualifier": "The Remix request enum exposes FLASH, but the pricing table has no Ideogram 4.0 Flash rate and the Generate reference says Flash is not yet available.", "source_ids": [ "remix-api", "generate-api", "pricing" ], "state": "unknown" }, { "amount": 0.03, "applies_when": [ "rendering_speed=TURBO" ], "denomination": "USD", "id": "image-remix-turbo", "kind": "metered", "per": 1, "profile_id": "image-remix", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.06, "applies_when": [ "rendering_speed=DEFAULT" ], "denomination": "USD", "id": "image-remix-default", "kind": "metered", "per": 1, "profile_id": "image-remix", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.1, "applies_when": [ "rendering_speed=QUALITY" ], "denomination": "USD", "id": "image-remix-quality", "kind": "metered", "per": 1, "profile_id": "image-remix", "source_ids": [ "pricing" ], "state": "known", "unit": "output_image" }, { "id": "magic-prompt-request", "profile_id": "magic-prompt", "qualifier": "The production V4 Magic Prompt endpoint has no published price; the free ideogram-4-v1 service described by the open package is a different system.", "source_ids": [ "magic-prompt-api", "pricing", "open-prompting" ], "state": "unknown" }, { "amount": 0.015, "denomination": "USD", "id": "describe-v4-input", "kind": "metered", "per": 1, "profile_id": "image-to-structured-prompt", "source_ids": [ "pricing" ], "state": "known", "unit": "input_image" }, { "id": "open-weights-runtime-compute", "profile_id": "open-weights-text-to-image", "qualifier": "Ideogram publishes no universal per-output cost for self-hosted inference; cost depends on the compute provisioned by the operator.", "source_ids": [ "model-page", "open-inference" ], "state": "unknown" } ], "source_ids": [ "pricing", "open-prompting", "model-page", "open-inference" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ideogram.ai/models/4.0/" }, { "id": "release-announcement", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://ideogram.ai/news/ideogram-4.0/" }, { "id": "release-blog", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://ideogram.ai/blog/ideogram-4.0/" }, { "id": "api-overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://ideogram.ai/api-learn/" }, { "id": "generate-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://developer.ideogram.ai/api-reference/api-reference/generate-v4" }, { "id": "generate-async-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://developer.ideogram.ai/api-reference/api-reference/generate-v4-async" }, { "id": "remix-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://developer.ideogram.ai/api-reference/api-reference/remix-v4" }, { "id": "magic-prompt-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://developer.ideogram.ai/api-reference/api-reference/magic-prompt-v4" }, { "id": "describe-api", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://developer.ideogram.ai/api-reference/api-reference/describe-v4" }, { "id": "webhooks-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://developer.ideogram.ai/ideogram-api/webhooks" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://ideogram.ai/api-pricing/" }, { "id": "open-repository", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://github.com/ideogram-oss/ideogram4" }, { "id": "open-inference", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://github.com/ideogram-oss/ideogram4/blob/main/docs/inference.md" }, { "id": "open-prompting", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://github.com/ideogram-oss/ideogram4/blob/main/docs/prompting.md" }, { "id": "open-safety", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://github.com/ideogram-oss/ideogram4/blob/main/docs/safety.md" }, { "id": "nf4-model-card", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://huggingface.co/ideogram-ai/ideogram-4-nf4" }, { "id": "fp8-model-card", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://huggingface.co/ideogram-ai/ideogram-4-fp8" }, { "id": "diffusers-model-card", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://huggingface.co/ideogram-ai/ideogram-4-nf4-diffusers" } ], "verification": { "state": "unverified" } }, { "capability_profiles": [ { "duration": { "max": 10, "min": 5, "mode": "range", "source_ids": [ "user-guide", "model-faq" ], "state": "supported", "step": 5, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-field-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-text-to-video-sdr", "native_audio": { "source_ids": [ "model-faq" ], "state": "unsupported" }, "size": { "mode": "exact_set", "options": [ { "id": "draft", "label": "Draft Mode", "source_ids": [ "model-faq", "pricing" ] }, { "id": "540p", "source_ids": [ "user-guide", "model-faq", "pricing" ] }, { "id": "720p", "source_ids": [ "user-guide", "model-faq", "pricing" ] }, { "id": "1080p", "label": "native 1080p", "source_ids": [ "user-guide", "model-faq", "pricing" ] } ], "source_ids": [ "user-guide", "model-faq", "pricing" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "user-guide", "model-faq", "model-field-guide" ], "task": "text_to_video", "variants": [ "SDR" ] }, { "duration": { "max": 10, "min": 5, "mode": "range", "source_ids": [ "user-guide", "model-faq" ], "state": "supported", "step": 5, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-field-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-text-to-video-hdr", "native_audio": { "source_ids": [ "model-faq" ], "state": "unsupported" }, "size": { "mode": "exact_set", "options": [ { "id": "540p", "source_ids": [ "model-faq", "credit-guide" ] }, { "id": "720p", "source_ids": [ "model-faq", "credit-guide" ] }, { "id": "1080p", "source_ids": [ "model-faq", "credit-guide" ] } ], "source_ids": [ "model-faq", "credit-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "user-guide", "model-faq", "model-field-guide" ], "task": "text_to_video", "variants": [ "HDR" ] }, { "delivery_profiles": [ { "default_format": "exr", "formats": [ "exr" ], "id": "openexr-download", "source_ids": [ "color-guide" ], "state": "supported", "transport": "download" } ], "duration": { "max": 10, "min": 5, "mode": "range", "source_ids": [ "user-guide", "model-faq" ], "state": "supported", "step": 5, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-field-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-text-to-video-hdr-exr", "native_audio": { "source_ids": [ "model-faq" ], "state": "unsupported" }, "size": { "mode": "exact_set", "options": [ { "id": "540p", "source_ids": [ "color-guide", "credit-guide" ] }, { "id": "720p", "source_ids": [ "color-guide", "credit-guide" ] } ], "source_ids": [ "color-guide", "credit-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "user-guide", "model-faq", "color-guide" ], "task": "text_to_video", "variants": [ "HDR+EXR" ] }, { "duration": { "max": 5, "min": 5, "mode": "range", "source_ids": [ "user-guide", "model-faq" ], "state": "supported", "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-field-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-image-to-video-sdr", "native_audio": { "source_ids": [ "model-faq" ], "state": "unsupported" }, "reference_inputs": [ { "max_count": 2, "media_type": "image", "min_count": 1, "position_roles": [ "start_image", "end_image" ], "role": "keyframe_sequence", "source_ids": [ "keyframes-guide", "model-field-guide" ], "state": "supported" }, { "media_type": "image", "role": "character_reference", "source_ids": [ "model-faq" ], "state": "unsupported" } ], "size": { "mode": "exact_set", "options": [ { "id": "draft", "label": "Draft Mode", "source_ids": [ "model-faq", "pricing" ] }, { "id": "540p", "source_ids": [ "user-guide", "model-faq", "pricing" ] }, { "id": "720p", "source_ids": [ "user-guide", "model-faq", "pricing" ] }, { "id": "1080p", "label": "native 1080p", "source_ids": [ "user-guide", "model-faq", "pricing" ] } ], "source_ids": [ "user-guide", "model-faq", "pricing" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "user-guide", "model-faq", "keyframes-guide" ], "task": "image_to_video", "variants": [ "SDR" ] }, { "duration": { "max": 5, "min": 5, "mode": "range", "source_ids": [ "user-guide", "model-faq" ], "state": "supported", "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-field-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-image-to-video-hdr", "native_audio": { "source_ids": [ "model-faq" ], "state": "unsupported" }, "reference_inputs": [ { "max_count": 2, "media_type": "image", "min_count": 1, "position_roles": [ "start_image", "end_image" ], "role": "keyframe_sequence", "source_ids": [ "keyframes-guide", "model-field-guide" ], "state": "supported" }, { "media_type": "image", "role": "character_reference", "source_ids": [ "model-faq" ], "state": "unsupported" } ], "size": { "mode": "exact_set", "options": [ { "id": "540p", "source_ids": [ "model-faq", "credit-guide" ] }, { "id": "720p", "source_ids": [ "model-faq", "credit-guide" ] }, { "id": "1080p", "source_ids": [ "model-faq", "credit-guide" ] } ], "source_ids": [ "model-faq", "credit-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "user-guide", "model-faq", "keyframes-guide" ], "task": "image_to_video", "variants": [ "HDR" ] }, { "delivery_profiles": [ { "default_format": "exr", "formats": [ "exr" ], "id": "openexr-download", "source_ids": [ "color-guide" ], "state": "supported", "transport": "download" } ], "duration": { "max": 5, "min": 5, "mode": "range", "source_ids": [ "user-guide", "model-faq" ], "state": "supported", "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-field-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-image-to-video-hdr-exr", "native_audio": { "source_ids": [ "model-faq" ], "state": "unsupported" }, "reference_inputs": [ { "max_count": 2, "media_type": "image", "min_count": 1, "position_roles": [ "start_image", "end_image" ], "role": "keyframe_sequence", "source_ids": [ "keyframes-guide", "model-field-guide" ], "state": "supported" }, { "media_type": "image", "role": "character_reference", "source_ids": [ "model-faq" ], "state": "unsupported" } ], "size": { "mode": "exact_set", "options": [ { "id": "540p", "source_ids": [ "color-guide", "credit-guide" ] }, { "id": "720p", "source_ids": [ "color-guide", "credit-guide" ] } ], "source_ids": [ "color-guide", "credit-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "user-guide", "model-faq", "keyframes-guide", "color-guide" ], "task": "image_to_video", "variants": [ "HDR+EXR" ] }, { "controls": [ { "mode": "exact_set", "name": "modify_mode", "source_ids": [ "model-field-guide" ], "state": "supported", "values": [ "Adhere", "Flex", "Reimagine" ] }, { "mode": "exact_set", "name": "modify_intensity", "source_ids": [ "model-field-guide" ], "state": "supported", "values": [ "1", "2", "3" ] }, { "name": "hdr_output", "source_ids": [ "model-faq", "model-field-guide" ], "state": "unsupported" }, { "name": "exr_output", "source_ids": [ "model-faq", "model-field-guide" ], "state": "unsupported" } ], "duration": { "source_ids": [ "user-guide", "model-faq" ], "state": "unknown" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-field-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-video-modify", "native_audio": { "source_ids": [ "model-faq" ], "state": "unsupported" }, "reference_inputs": [ { "constraints": [ "format_list=non_exhaustive" ], "duration_unit": "second", "formats": [ "mp4", "mov" ], "max_count": 1, "max_duration": 18, "media_type": "video", "min_count": 1, "role": "start_video", "source_ids": [ "user-guide", "model-faq" ], "state": "supported" }, { "max_count": 2, "media_type": "image", "min_count": 0, "position_roles": [ "start_image", "end_image" ], "role": "keyframe_sequence", "source_ids": [ "model-field-guide" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "id": "draft", "label": "Draft Mode", "source_ids": [ "pricing" ] }, { "id": "540p", "source_ids": [ "pricing", "credit-guide" ] }, { "id": "720p", "source_ids": [ "pricing", "credit-guide" ] }, { "id": "1080p", "source_ids": [ "pricing", "credit-guide" ] } ], "source_ids": [ "pricing", "credit-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "user-guide", "model-faq", "model-field-guide" ], "task": "video_edit", "variants": [ "SDR" ] }, { "duration": { "source_ids": [ "user-guide", "model-faq", "extend-guide" ], "state": "unknown" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-field-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-video-extension", "native_audio": { "source_ids": [ "model-faq" ], "state": "unsupported" }, "reference_inputs": [ { "max_count": 1, "media_type": "video", "min_count": 1, "role": "start_video", "source_ids": [ "extend-guide" ], "state": "supported" }, { "max_count": 1, "media_type": "image", "min_count": 0, "role": "end_image", "source_ids": [ "extend-guide" ], "state": "supported" } ], "size": { "source_ids": [ "extend-guide" ], "state": "unknown" }, "source_ids": [ "user-guide", "model-faq", "extend-guide" ], "task": "video_extension" }, { "duration": { "source_ids": [ "user-guide", "model-faq" ], "state": "unknown" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-field-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-video-loop", "native_audio": { "source_ids": [ "model-faq" ], "state": "unsupported" }, "size": { "mode": "exact_set", "options": [ { "id": "540p", "source_ids": [ "user-guide", "model-faq" ] }, { "id": "720p", "source_ids": [ "user-guide", "model-faq" ] }, { "id": "1080p", "source_ids": [ "user-guide", "model-faq" ] } ], "source_ids": [ "user-guide", "model-faq" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "user-guide", "model-faq" ], "task": "video_loop" }, { "duration": { "source_ids": [ "user-guide", "model-faq" ], "state": "unknown" }, "frame_rate": { "source_ids": [ "user-guide", "model-faq" ], "state": "unknown" }, "id": "web-video-upscale", "native_audio": { "source_ids": [ "user-guide", "model-faq" ], "state": "unknown" }, "reference_inputs": [ { "constraints": [ "input_resolution=540p_or_720p_or_1080p" ], "max_count": 1, "media_type": "video", "min_count": 1, "role": "start_video", "source_ids": [ "user-guide", "model-faq" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "id": "4K", "label": "4K upscale", "source_ids": [ "user-guide", "model-faq" ] } ], "source_ids": [ "user-guide", "model-faq" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "user-guide", "model-faq" ], "task": "video_upscale" } ], "conflicts": [ { "handling": "Use the exact model-specific FAQ and user-guide values; keep Modify output duration unknown because the 18-second claim is an input-video limit.", "path": "capability_profiles.web-text-to-video-*.duration,capability_profiles.web-image-to-video-*.duration,capability_profiles.web-video-modify.duration", "source_ids": [ "user-guide", "model-faq", "model-field-guide" ], "summary": "Ray3.14's model-specific FAQ and user guide state 5- or 10-second text-to-video, 5-second image-to-video, and up to 18-second Modify input, while a summary table in Luma's video-model field guide lists 4, 8, and 12 seconds with roughly 18 seconds of orchestration." }, { "handling": "Expose 540p and 720p in HDR+EXR profiles and leave 1080p omitted until Luma resolves the serving-versus-pricing disagreement.", "path": "capability_profiles.web-*-hdr-exr.size.options", "source_ids": [ "color-guide", "credit-guide", "model-faq" ], "summary": "Luma's color-space guide says EXR export is available at 540p and 720p, while an official credit surface also publishes 1080p HDR+EXR charges." }, { "handling": "Represent positional start/end keyframes as supported and the separate unpositioned character-reference role as unsupported.", "path": "capability_profiles.web-image-to-video-*.reference_inputs", "source_ids": [ "model-faq", "keyframes-guide", "model-field-guide" ], "summary": "The model FAQ says the reference-image feature is unavailable, while Luma's keyframe guide and field guide document start and end keyframes." }, { "handling": "Use unsupported for same-generation native audio and treat the field-guide statement as the separate Add Audio workflow.", "path": "capability_profiles.*.native_audio.state", "source_ids": [ "model-faq", "model-field-guide" ], "summary": "The model FAQ explicitly says Ray3.14 has no native audio, while the broader field guide says audio generation is available in supported user interfaces." }, { "handling": "Do not create an API identifier or API capability profile for Ray3.14.", "path": "api_identifiers", "source_ids": [ "model-faq", "api-overview", "agents-model-guide", "agents-generation-reference" ], "summary": "The exact Ray3.14 FAQ says the model is Dream Machine Web-only, while Luma's API marketing page mentions Ray3.14 under other models without publishing a serving ID or parameter contract; current API enums list other Ray models." } ], "documentation_state": "documented", "limitations": [ { "id": "public-api-unavailable", "source_ids": [ "model-faq", "agents-model-guide", "agents-generation-reference" ], "summary": "Luma states that Ray3.14 is available only in Dream Machine Web and is not available through its public API." }, { "id": "character-reference", "source_ids": [ "model-faq", "keyframes-guide" ], "summary": "Luma says Ray3.14 lacks character consistency and the unpositioned reference-image feature; positional start and end keyframes remain available." }, { "id": "reframe", "source_ids": [ "model-faq" ], "summary": "Luma states that Ray3.14 cannot be used with Reframe." }, { "id": "native-audio", "source_ids": [ "model-faq", "model-field-guide" ], "summary": "Luma states that Ray3.14 does not generate native audio; audio can be added in a separate post-generation workflow." }, { "id": "modify-hdr-exr", "source_ids": [ "model-faq", "model-field-guide" ], "summary": "Luma states that HDR and EXR are not supported in Modify." }, { "id": "extension-length", "source_ids": [ "user-guide", "model-faq" ], "summary": "Luma states that Ray3.14 video can be extended up to approximately 30 seconds." } ], "model": { "aliases": [ "Ray3 Pi", "Ray3Pi", "Ray3.14 (Pi)" ], "id": "luma-ai/ray3-14", "lab": "Luma AI", "modality": "video", "name": "Ray3.14", "source_ids": [ "user-guide", "model-faq", "release" ], "status": "available" }, "pricing": { "charges": [ { "amount": 4, "applies_when": [ "resolution=draft" ], "denomination": "credit", "id": "t2v-sdr-draft", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-sdr", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 10, "applies_when": [ "resolution=540p" ], "denomination": "credit", "id": "t2v-sdr-540p", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-sdr", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 20, "applies_when": [ "resolution=720p" ], "denomination": "credit", "id": "t2v-sdr-720p", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-sdr", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 80, "applies_when": [ "resolution=1080p" ], "denomination": "credit", "id": "t2v-sdr-1080p", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-sdr", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 4, "applies_when": [ "resolution=draft" ], "denomination": "credit", "id": "i2v-sdr-draft", "kind": "metered", "per": 1, "profile_id": "web-image-to-video-sdr", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 10, "applies_when": [ "resolution=540p" ], "denomination": "credit", "id": "i2v-sdr-540p", "kind": "metered", "per": 1, "profile_id": "web-image-to-video-sdr", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 20, "applies_when": [ "resolution=720p" ], "denomination": "credit", "id": "i2v-sdr-720p", "kind": "metered", "per": 1, "profile_id": "web-image-to-video-sdr", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 80, "applies_when": [ "resolution=1080p" ], "denomination": "credit", "id": "i2v-sdr-1080p", "kind": "metered", "per": 1, "profile_id": "web-image-to-video-sdr", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 200, "applies_when": [ "resolution=540p", "duration=5_seconds" ], "denomination": "credit", "id": "t2v-hdr-540p-5s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 400, "applies_when": [ "resolution=540p", "duration=10_seconds" ], "denomination": "credit", "id": "t2v-hdr-540p-10s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 400, "applies_when": [ "resolution=720p", "duration=5_seconds" ], "denomination": "credit", "id": "t2v-hdr-720p-5s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 800, "applies_when": [ "resolution=720p", "duration=10_seconds" ], "denomination": "credit", "id": "t2v-hdr-720p-10s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 1600, "applies_when": [ "resolution=1080p", "duration=5_seconds" ], "denomination": "credit", "id": "t2v-hdr-1080p-5s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 3200, "applies_when": [ "resolution=1080p", "duration=10_seconds" ], "denomination": "credit", "id": "t2v-hdr-1080p-10s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 200, "applies_when": [ "resolution=540p", "duration=5_seconds" ], "denomination": "credit", "id": "i2v-hdr-540p-5s", "kind": "metered", "per": 1, "profile_id": "web-image-to-video-hdr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 400, "applies_when": [ "resolution=720p", "duration=5_seconds" ], "denomination": "credit", "id": "i2v-hdr-720p-5s", "kind": "metered", "per": 1, "profile_id": "web-image-to-video-hdr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 1600, "applies_when": [ "resolution=1080p", "duration=5_seconds" ], "denomination": "credit", "id": "i2v-hdr-1080p-5s", "kind": "metered", "per": 1, "profile_id": "web-image-to-video-hdr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 350, "applies_when": [ "resolution=540p", "duration=5_seconds" ], "denomination": "credit", "id": "t2v-hdr-exr-540p-5s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr-exr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 700, "applies_when": [ "resolution=540p", "duration=10_seconds" ], "denomination": "credit", "id": "t2v-hdr-exr-540p-10s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr-exr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 700, "applies_when": [ "resolution=720p", "duration=5_seconds" ], "denomination": "credit", "id": "t2v-hdr-exr-720p-5s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr-exr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 1400, "applies_when": [ "resolution=720p", "duration=10_seconds" ], "denomination": "credit", "id": "t2v-hdr-exr-720p-10s", "kind": "metered", "per": 1, "profile_id": "web-text-to-video-hdr-exr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 350, "applies_when": [ "resolution=540p", "duration=5_seconds" ], "denomination": "credit", "id": "i2v-hdr-exr-540p-5s", "kind": "metered", "per": 1, "profile_id": "web-image-to-video-hdr-exr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 700, "applies_when": [ "resolution=720p", "duration=5_seconds" ], "denomination": "credit", "id": "i2v-hdr-exr-720p-5s", "kind": "metered", "per": 1, "profile_id": "web-image-to-video-hdr-exr", "source_ids": [ "credit-guide", "model-faq" ], "state": "known", "unit": "video" }, { "amount": 12, "applies_when": [ "resolution=draft" ], "denomination": "credit", "id": "modify-draft", "kind": "metered", "per": 1, "profile_id": "web-video-modify", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 24, "applies_when": [ "resolution=540p" ], "denomination": "credit", "id": "modify-540p", "kind": "metered", "per": 1, "profile_id": "web-video-modify", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 48, "applies_when": [ "resolution=720p" ], "denomination": "credit", "id": "modify-720p", "kind": "metered", "per": 1, "profile_id": "web-video-modify", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 192, "applies_when": [ "resolution=1080p" ], "denomination": "credit", "id": "modify-1080p", "kind": "metered", "per": 1, "profile_id": "web-video-modify", "source_ids": [ "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.0033, "denomination": "USD", "id": "credit-purchase", "kind": "metered", "per": 1, "qualifier": "Dream Machine credit price; top-ups start at USD 4 for 1,200 credits.", "source_ids": [ "credit-guide" ], "state": "known", "unit": "credit" }, { "id": "extension", "profile_id": "web-video-extension", "source_ids": [ "pricing", "credit-guide" ], "state": "unknown" }, { "id": "loop", "profile_id": "web-video-loop", "source_ids": [ "pricing", "credit-guide" ], "state": "unknown" }, { "id": "upscale", "profile_id": "web-video-upscale", "source_ids": [ "pricing", "credit-guide" ], "state": "unknown" } ], "source_ids": [ "pricing", "credit-guide", "model-faq" ], "state": "partial" }, "schema_version": 1, "sources": [ { "id": "user-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/learning-hub/ray314-user-guide" }, { "id": "model-faq", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/learning-hub/ray3-faq" }, { "id": "model-field-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/learning-center/articles/luma-video-models-field-guide" }, { "id": "keyframes-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/learning-hub/how-to-use-keyframes" }, { "id": "extend-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/learning-hub/how-to-use-extend" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/pricing" }, { "id": "credit-guide", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/learning-hub/dream-machine-credit-system" }, { "id": "release", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/news/ray3_14" }, { "id": "color-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/learning-center/articles/color-space-field-guide" }, { "id": "changelog", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/changelog" }, { "id": "api-overview", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://lumalabs.ai/api" }, { "id": "agents-docs", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.agents.lumalabs.ai/" }, { "id": "agents-model-guide", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.agents.lumalabs.ai/guides/model/" }, { "id": "agents-generation-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.agents.lumalabs.ai/api/resources/generations/methods/create" }, { "id": "legacy-llms", "kind": "api_schema", "retrieved_on": "2026-08-10", "url": "https://docs.lumalabs.ai/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-catalog", "t2v-reference", "i2v-reference" ], "value": "MiniMax-Hailuo-2.3" } ], "capability_profiles": [ { "api_mode": "MiniMax-Hailuo-2.3", "controls": [ { "default": "6", "mode": "exact_set", "name": "duration", "source_ids": [ "t2v-reference" ], "state": "supported", "unit": "second", "values": [ "6", "10" ] }, { "default": "768P", "mode": "exact_set", "name": "resolution", "source_ids": [ "t2v-reference" ], "state": "supported", "values": [ "768P", "1080P" ] }, { "default": "true", "mode": "exact_set", "name": "prompt_optimizer", "source_ids": [ "t2v-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "fast_pretreatment", "source_ids": [ "t2v-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "mode": "exact_set", "name": "camera_motion_command", "source_ids": [ "t2v-reference", "video-guide" ], "state": "supported", "values": [ "[Truck left]", "[Truck right]", "[Pan left]", "[Pan right]", "[Push in]", "[Pull out]", "[Pedestal up]", "[Pedestal down]", "[Tilt up]", "[Tilt down]", "[Zoom in]", "[Zoom out]", "[Shake]", "[Tracking shot]", "[Static shot]" ] } ], "delivery_profiles": [ { "endpoint": "GET /v1/query/video_generation?task_id={task_id}", "id": "task-query", "source_ids": [ "query-reference" ], "state": "supported", "transport": "asynchronous_task_status" }, { "endpoint": "GET /v1/files/retrieve?file_id={file_id}", "id": "file-download", "source_ids": [ "download-reference" ], "state": "supported", "transport": "download_url" } ], "duration": { "max": 10, "min": 6, "mode": "range", "source_ids": [ "t2v-reference" ], "state": "supported", "step": 4, "unit": "second" }, "endpoint": "POST https://api.minimax.io/v1/video_generation", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-catalog" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "api-text-to-video", "native_audio": { "source_ids": [ "model-catalog", "t2v-reference" ], "state": "unknown" }, "size": { "default": "768P", "mode": "exact_set", "options": [ { "id": "768P", "render_modes": [ "duration=6_seconds", "duration=10_seconds" ], "source_ids": [ "t2v-reference" ] }, { "id": "1080P", "render_modes": [ "duration=6_seconds" ], "source_ids": [ "t2v-reference" ] } ], "source_ids": [ "t2v-reference" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "t2v-reference", "model-catalog" ], "task": "text_to_video", "text_input": { "max": 2000, "source_ids": [ "t2v-reference" ], "state": "supported", "unit": "character" } }, { "api_mode": "MiniMax-Hailuo-2.3", "controls": [ { "default": "6", "mode": "exact_set", "name": "duration", "source_ids": [ "i2v-reference" ], "state": "supported", "unit": "second", "values": [ "6", "10" ] }, { "default": "768P", "mode": "exact_set", "name": "resolution", "source_ids": [ "i2v-reference" ], "state": "supported", "values": [ "768P", "1080P" ] }, { "default": "true", "mode": "exact_set", "name": "prompt_optimizer", "source_ids": [ "i2v-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "fast_pretreatment", "source_ids": [ "i2v-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "mode": "exact_set", "name": "camera_motion_command", "source_ids": [ "i2v-reference", "video-guide" ], "state": "supported", "values": [ "[Truck left]", "[Truck right]", "[Pan left]", "[Pan right]", "[Push in]", "[Pull out]", "[Pedestal up]", "[Pedestal down]", "[Tilt up]", "[Tilt down]", "[Zoom in]", "[Zoom out]", "[Shake]", "[Tracking shot]", "[Static shot]" ] } ], "delivery_profiles": [ { "endpoint": "GET /v1/query/video_generation?task_id={task_id}", "id": "task-query", "source_ids": [ "query-reference" ], "state": "supported", "transport": "asynchronous_task_status" }, { "endpoint": "GET /v1/files/retrieve?file_id={file_id}", "id": "file-download", "source_ids": [ "download-reference" ], "state": "supported", "transport": "download_url" } ], "duration": { "max": 10, "min": 6, "mode": "range", "source_ids": [ "i2v-reference" ], "state": "supported", "step": 4, "unit": "second" }, "endpoint": "POST https://api.minimax.io/v1/video_generation", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-catalog" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "api-image-to-video", "native_audio": { "source_ids": [ "model-catalog", "i2v-reference" ], "state": "unknown" }, "reference_inputs": [ { "constraints": [ "file_size_less_than=20MB", "short_edge_greater_than=300px", "input_aspect_ratio_min=2:5", "input_aspect_ratio_max=5:2" ], "encodings": [ "https_url", "base64_data_uri" ], "formats": [ "jpg", "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "i2v-reference" ], "state": "supported" }, { "media_type": "image", "role": "end_image", "source_ids": [ "i2v-reference", "fl2v-reference" ], "state": "unknown" }, { "media_type": "image", "role": "image_reference", "source_ids": [ "i2v-reference", "s2v-reference" ], "state": "unknown" } ], "size": { "default": "768P", "mode": "exact_set", "options": [ { "id": "768P", "render_modes": [ "duration=6_seconds", "duration=10_seconds" ], "source_ids": [ "i2v-reference" ] }, { "id": "1080P", "render_modes": [ "duration=6_seconds" ], "source_ids": [ "i2v-reference" ] } ], "source_ids": [ "i2v-reference" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "i2v-reference", "model-catalog" ], "task": "image_to_video", "text_input": { "max": 2000, "source_ids": [ "i2v-reference" ], "state": "supported", "unit": "character" } } ], "conflicts": [ { "handling": "Use available for current callable access and preserve the lab's Legacy label as conflicting lifecycle provenance.", "path": "model.status", "source_ids": [ "model-catalog", "t2v-reference", "i2v-reference", "paygo-pricing" ], "summary": "MiniMax places Hailuo 2.3 under Legacy Models while its exact model ID remains accepted by the live text-to-video and image-to-video APIs and remains present in current lab pricing." } ], "documentation_state": "documented", "model": { "id": "minimax/minimax-hailuo-2-3", "lab": "MiniMax", "modality": "video", "name": "MiniMax Hailuo 2.3", "source_ids": [ "model-catalog", "t2v-reference", "i2v-reference", "model-release-notes" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.28, "applies_when": [ "resolution=768P", "duration=6_seconds" ], "denomination": "USD", "id": "768p-6s-output", "kind": "metered", "per": 1, "source_ids": [ "paygo-pricing" ], "state": "known", "unit": "video" }, { "amount": 0.56, "applies_when": [ "resolution=768P", "duration=10_seconds" ], "denomination": "USD", "id": "768p-10s-output", "kind": "metered", "per": 1, "source_ids": [ "paygo-pricing" ], "state": "known", "unit": "video" }, { "amount": 0.49, "applies_when": [ "resolution=1080P", "duration=6_seconds" ], "denomination": "USD", "id": "1080p-6s-output", "kind": "metered", "per": 1, "source_ids": [ "paygo-pricing" ], "state": "known", "unit": "video" } ], "source_ids": [ "paygo-pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-catalog", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/guides/models-intro" }, { "id": "video-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/guides/video-generation" }, { "id": "t2v-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/video-generation-t2v" }, { "id": "i2v-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v" }, { "id": "fl2v-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/video-generation-fl2v" }, { "id": "s2v-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/video-generation-s2v" }, { "id": "query-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/video-generation-query" }, { "id": "download-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/video-generation-download" }, { "id": "paygo-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/guides/pricing-paygo" }, { "id": "video-package-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/guides/pricing-video" }, { "id": "api-release-notes", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/release-notes/apis" }, { "id": "model-release-notes", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/release-notes/models" }, { "id": "llms", "kind": "api_schema", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-catalog", "i2v-reference" ], "value": "MiniMax-Hailuo-2.3-Fast" } ], "capability_profiles": [ { "api_mode": "MiniMax-Hailuo-2.3-Fast", "controls": [ { "default": "6", "mode": "exact_set", "name": "duration", "source_ids": [ "i2v-reference" ], "state": "supported", "unit": "second", "values": [ "6", "10" ] }, { "default": "768P", "mode": "exact_set", "name": "resolution", "source_ids": [ "i2v-reference" ], "state": "supported", "values": [ "768P", "1080P" ] }, { "default": "true", "mode": "exact_set", "name": "prompt_optimizer", "source_ids": [ "i2v-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "fast_pretreatment", "source_ids": [ "i2v-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "mode": "exact_set", "name": "camera_motion_command", "source_ids": [ "i2v-reference", "video-guide" ], "state": "supported", "values": [ "[Truck left]", "[Truck right]", "[Pan left]", "[Pan right]", "[Push in]", "[Pull out]", "[Pedestal up]", "[Pedestal down]", "[Tilt up]", "[Tilt down]", "[Zoom in]", "[Zoom out]", "[Shake]", "[Tracking shot]", "[Static shot]" ] } ], "delivery_profiles": [ { "endpoint": "GET /v1/query/video_generation?task_id={task_id}", "id": "task-query", "source_ids": [ "query-reference" ], "state": "supported", "transport": "asynchronous_task_status" }, { "endpoint": "GET /v1/files/retrieve?file_id={file_id}", "id": "file-download", "source_ids": [ "download-reference" ], "state": "supported", "transport": "download_url" } ], "duration": { "max": 10, "min": 6, "mode": "range", "source_ids": [ "i2v-reference" ], "state": "supported", "step": 4, "unit": "second" }, "endpoint": "POST https://api.minimax.io/v1/video_generation", "frame_rate": { "mode": "exact_set", "source_ids": [ "model-catalog" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "api-image-to-video", "native_audio": { "source_ids": [ "model-catalog", "i2v-reference" ], "state": "unknown" }, "reference_inputs": [ { "constraints": [ "file_size_less_than=20MB", "short_edge_greater_than=300px", "input_aspect_ratio_min=2:5", "input_aspect_ratio_max=5:2" ], "encodings": [ "https_url", "base64_data_uri" ], "formats": [ "jpg", "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "i2v-reference" ], "state": "supported" }, { "media_type": "image", "role": "end_image", "source_ids": [ "i2v-reference", "fl2v-reference" ], "state": "unknown" }, { "media_type": "image", "role": "image_reference", "source_ids": [ "i2v-reference", "s2v-reference" ], "state": "unknown" } ], "size": { "default": "768P", "mode": "exact_set", "options": [ { "id": "768P", "render_modes": [ "duration=6_seconds", "duration=10_seconds" ], "source_ids": [ "i2v-reference" ] }, { "id": "1080P", "render_modes": [ "duration=6_seconds" ], "source_ids": [ "i2v-reference" ] } ], "source_ids": [ "i2v-reference" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "i2v-reference", "model-catalog" ], "task": "image_to_video", "text_input": { "max": 2000, "source_ids": [ "i2v-reference" ], "state": "supported", "unit": "character" } } ], "conflicts": [ { "handling": "Use available for current callable access and preserve the lab's Legacy label as conflicting lifecycle provenance.", "path": "model.status", "source_ids": [ "model-catalog", "i2v-reference", "paygo-pricing" ], "summary": "MiniMax places Hailuo 2.3 Fast under Legacy Models while its exact model ID remains accepted by the live image-to-video API and remains present in current lab pricing." } ], "documentation_state": "documented", "model": { "id": "minimax/minimax-hailuo-2-3-fast", "lab": "MiniMax", "modality": "video", "name": "MiniMax Hailuo 2.3 Fast", "source_ids": [ "model-catalog", "i2v-reference", "model-release-notes" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.19, "applies_when": [ "resolution=768P", "duration=6_seconds" ], "denomination": "USD", "id": "768p-6s-output", "kind": "metered", "per": 1, "source_ids": [ "paygo-pricing" ], "state": "known", "unit": "video" }, { "amount": 0.32, "applies_when": [ "resolution=768P", "duration=10_seconds" ], "denomination": "USD", "id": "768p-10s-output", "kind": "metered", "per": 1, "source_ids": [ "paygo-pricing" ], "state": "known", "unit": "video" }, { "amount": 0.33, "applies_when": [ "resolution=1080P", "duration=6_seconds" ], "denomination": "USD", "id": "1080p-6s-output", "kind": "metered", "per": 1, "source_ids": [ "paygo-pricing" ], "state": "known", "unit": "video" } ], "source_ids": [ "paygo-pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-catalog", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/guides/models-intro" }, { "id": "video-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/guides/video-generation" }, { "id": "i2v-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/video-generation-i2v" }, { "id": "fl2v-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/video-generation-fl2v" }, { "id": "s2v-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/video-generation-s2v" }, { "id": "query-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/video-generation-query" }, { "id": "download-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/video-generation-download" }, { "id": "paygo-pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/guides/pricing-paygo" }, { "id": "video-package-pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/guides/pricing-video" }, { "id": "api-release-notes", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/release-notes/apis" }, { "id": "model-release-notes", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/release-notes/models" }, { "id": "llms", "kind": "api_schema", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "music-reference", "paygo-pricing" ], "value": "music-2.6" }, { "kind": "model_id", "source_ids": [ "music-reference", "paygo-pricing" ], "value": "music-2.6-free" } ], "capability_profiles": [ { "api_mode": "music-2.6", "api_mode_aliases": [ "music-2.6-free" ], "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 128, 256 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 16000, 24000, 32000, 44100 ], "source_ids": [ "music-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 128, 256 ], "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 16000, 24000, 32000, 44100 ], "source_ids": [ "music-reference" ] }, { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 128, 256 ], "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 16000, 24000, 32000, 44100 ], "source_ids": [ "music-reference" ] } ], "controls": [ { "max": 3500, "min": 1, "mode": "range", "name": "lyrics_length_when_present", "source_ids": [ "music-reference" ], "state": "supported", "step": 1, "unit": "character" }, { "default": "false", "mode": "exact_set", "name": "stream", "source_ids": [ "music-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "hex", "mode": "exact_set", "name": "output_format", "source_ids": [ "music-reference" ], "state": "supported", "values": [ "url", "hex" ] }, { "mode": "exact_set", "name": "sample_rate", "source_ids": [ "music-reference" ], "state": "supported", "unit": "hertz", "values": [ "16000", "24000", "32000", "44100" ] }, { "mode": "exact_set", "name": "bitrate", "source_ids": [ "music-reference" ], "state": "supported", "unit": "bit_per_second", "values": [ "32000", "64000", "128000", "256000" ] }, { "mode": "exact_set", "name": "audio_format", "source_ids": [ "music-reference" ], "state": "supported", "values": [ "mp3", "wav", "pcm" ] }, { "default": "false", "mode": "exact_set", "name": "lyrics_optimizer", "source_ids": [ "music-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "is_instrumental", "source_ids": [ "music-reference" ], "state": "supported", "values": [ "true", "false" ] } ], "delivery_profiles": [ { "default_format": "hex", "endpoint": "POST /v1/music_generation", "formats": [ "hex" ], "id": "hex-response", "source_ids": [ "music-reference" ], "state": "supported", "transport": "hex_in_response" }, { "endpoint": "POST /v1/music_generation", "formats": [ "url" ], "id": "temporary-url", "source_ids": [ "music-reference" ], "state": "supported", "transport": "temporary_url" }, { "endpoint": "POST /v1/music_generation", "formats": [ "hex" ], "id": "streaming-hex", "source_ids": [ "music-reference" ], "state": "supported", "transport": "http_stream" } ], "duration": { "source_ids": [ "music-reference", "paygo-pricing" ], "state": "unknown" }, "endpoint": "POST https://api.minimax.io/v1/music_generation", "frame_rate": { "source_ids": [ "music-reference" ], "state": "not_applicable" }, "id": "music-generation", "native_audio": { "source_ids": [ "music-reference" ], "state": "not_applicable" }, "size": { "source_ids": [ "music-reference" ], "state": "not_applicable" }, "source_ids": [ "music-reference" ], "task": "music_generation", "text_input": { "max": 2000, "source_ids": [ "music-reference" ], "state": "supported", "unit": "character" } } ], "conflicts": [ { "handling": "Keep the capability duration unknown and preserve the five-minute phrase only as a billing qualifier.", "path": "capability_profiles.music-generation.duration", "source_ids": [ "music-reference", "paygo-pricing" ], "summary": "MiniMax prices each paid generation as up to five minutes of music, but the live request schema exposes no duration control or explicit output-duration constraint." } ], "documentation_state": "documented", "model": { "id": "minimax/minimax-music-2-6", "lab": "MiniMax", "modality": "audio", "name": "MiniMax Music 2.6", "source_ids": [ "music-reference", "paygo-pricing" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.15, "applies_when": [ "model_id=music-2.6", "output_duration<=5_minutes" ], "denomination": "USD", "id": "paid-generation", "kind": "metered", "per": 1, "profile_id": "music-generation", "source_ids": [ "paygo-pricing" ], "state": "known", "unit": "music_generation" } ], "source_ids": [ "paygo-pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "music-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/music-generation" }, { "id": "paygo-pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/guides/pricing-paygo" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-guide", "http-reference", "websocket-reference", "async-reference" ], "value": "speech-2.8-hd" } ], "capability_profiles": [ { "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 128, 256 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "http-reference" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "http-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "http-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "http-reference" ] } ], "controls": [ { "default": "false", "mode": "exact_set", "name": "stream", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": 1, "max": 2, "min": 0.5, "mode": "range", "name": "speed", "source_ids": [ "http-reference" ], "state": "supported", "unit": "ratio" }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch", "source_ids": [ "http-reference" ], "state": "supported", "unit": "semitone" }, { "mode": "exact_set", "name": "emotion", "source_ids": [ "model-guide", "http-reference" ], "state": "supported", "unsupported_values": [ "fluent", "whisper" ], "values": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm" ] }, { "max": 99.99, "min": 0.01, "mode": "range", "name": "pause_duration", "source_ids": [ "http-reference" ], "state": "supported", "step": 0.01, "unit": "second" }, { "mode": "exact_set", "name": "interjection_tag", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "laughs", "chuckle", "coughs", "clear-throat", "groans", "breath", "pant", "inhale", "exhale", "gasps", "sniffs", "sighs", "snorts", "burps", "lip-smacking", "humming", "hissing", "emm", "sneezes" ] }, { "default": "false", "mode": "exact_set", "name": "text_normalization", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "latex_read", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "hex", "mode": "exact_set", "name": "output_delivery", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "hex", "url" ] }, { "default": "1", "mode": "exact_set", "name": "channel", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "1", "2" ] }, { "default": "false", "formats": [ "mp3" ], "mode": "exact_set", "name": "force_cbr", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "subtitle_enable", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "sentence", "mode": "exact_set", "name": "subtitle_type", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "sentence", "word", "word_streaming" ] }, { "default": 0, "max": 100, "min": -100, "mode": "range", "name": "voice_modify_pitch", "source_ids": [ "http-reference" ], "state": "supported", "unit": "relative" }, { "default": 0, "max": 100, "min": -100, "mode": "range", "name": "voice_modify_intensity", "source_ids": [ "http-reference" ], "state": "supported", "unit": "relative" }, { "default": 0, "max": 100, "min": -100, "mode": "range", "name": "voice_modify_timbre", "source_ids": [ "http-reference" ], "state": "supported", "unit": "relative" }, { "formats": [ "mp3", "wav", "flac" ], "mode": "exact_set", "name": "voice_sound_effect", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "POST https://api.minimax.io/v1/t2a_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "hex-http-response", "source_ids": [ "http-reference" ], "state": "supported", "transport": "json_hex" }, { "default_format": "mp3", "endpoint": "POST https://api-uw.minimax.io/v1/t2a_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "low-ttfa-http-response", "source_ids": [ "http-reference" ], "state": "supported", "transport": "json_hex" }, { "default_format": "mp3", "endpoint": "POST /v1/t2a_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "temporary-url", "source_ids": [ "http-reference" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "http-reference" ], "state": "unknown" }, "endpoint": "POST /v1/t2a_v2", "frame_rate": { "source_ids": [ "model-guide" ], "state": "not_applicable" }, "id": "text-to-speech-http", "native_audio": { "source_ids": [ "model-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "http-reference" ], "state": "supported" }, { "constraints": [ "weight_min=1", "weight_max=100" ], "count_scope": "unique", "max_count": 4, "media_type": "voice_id", "min_count": 1, "role": "voice_mix", "source_ids": [ "http-reference" ], "state": "supported" } ], "size": { "source_ids": [ "model-guide" ], "state": "not_applicable" }, "source_ids": [ "http-reference" ], "task": "text_to_speech", "text_input": { "max": 9999, "source_ids": [ "http-reference" ], "state": "supported", "unit": "character" } }, { "controls": [ { "default": 1, "max": 2, "min": 0.5, "mode": "range", "name": "speed", "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "ratio" }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch", "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "semitone" }, { "mode": "exact_set", "name": "emotion", "source_ids": [ "model-guide", "websocket-reference" ], "state": "supported", "unsupported_values": [ "fluent", "whisper" ], "values": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm" ] }, { "default": "32000", "mode": "exact_set", "name": "output_sample_rate", "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "hertz", "values": [ "8000", "16000", "22050", "24000", "32000", "44100" ] }, { "default": "128000", "formats": [ "mp3" ], "mode": "exact_set", "name": "mp3_bitrate", "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "bit_per_second", "values": [ "32000", "64000", "128000", "256000" ] }, { "default": "1", "mode": "exact_set", "name": "channel", "source_ids": [ "websocket-reference" ], "state": "supported", "values": [ "1", "2" ] }, { "default": "false", "mode": "exact_set", "name": "continuous_sound", "source_ids": [ "websocket-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "subtitle_enable", "source_ids": [ "websocket-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "sentence", "mode": "exact_set", "name": "subtitle_type", "source_ids": [ "websocket-reference" ], "state": "supported", "values": [ "sentence", "word", "word_streaming" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "WSS wss://api.minimax.io/ws/v1/t2a_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "websocket-hex-audio", "source_ids": [ "websocket-reference", "websocket-guide" ], "state": "supported", "transport": "websocket" } ], "duration": { "source_ids": [ "websocket-reference" ], "state": "unknown" }, "endpoint": "WSS /ws/v1/t2a_v2", "id": "text-to-speech-websocket", "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "websocket-reference" ], "state": "supported" } ], "source_ids": [ "websocket-reference", "websocket-guide" ], "task": "text_to_speech", "text_input": { "max": 10000, "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "character" } }, { "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 128, 256 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "async-reference" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "async-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "async-reference" ] }, { "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 12000, 16000, 24000, 48000 ], "source_ids": [ "async-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "async-reference" ] } ], "controls": [ { "default": 1, "max": 2, "min": 0.5, "mode": "range", "name": "speed", "source_ids": [ "async-reference" ], "state": "supported", "unit": "ratio" }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch", "source_ids": [ "async-reference" ], "state": "supported", "unit": "semitone" }, { "mode": "exact_set", "name": "emotion", "source_ids": [ "model-guide", "async-reference" ], "state": "supported", "unsupported_values": [ "fluent", "whisper" ], "values": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm" ] }, { "mode": "exact_set", "name": "interjection_tag", "source_ids": [ "async-reference" ], "state": "supported", "values": [ "laughs", "chuckle", "coughs", "clear-throat", "groans", "breath", "pant", "inhale", "exhale", "gasps", "sniffs", "sighs", "snorts", "burps", "lip-smacking", "humming", "hissing", "emm", "whistles", "sneezes", "crying", "applause" ] }, { "default": "32000", "mode": "exact_set", "name": "output_sample_rate", "source_ids": [ "async-reference" ], "state": "supported", "unit": "hertz", "values": [ "8000", "16000", "22050", "24000", "32000", "44100" ] }, { "default": "128000", "formats": [ "mp3" ], "mode": "exact_set", "name": "mp3_bitrate", "source_ids": [ "async-reference" ], "state": "supported", "unit": "bit_per_second", "values": [ "32000", "64000", "128000", "256000" ] }, { "default": "2", "mode": "exact_set", "name": "channel", "source_ids": [ "async-reference" ], "state": "supported", "values": [ "1", "2" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "GET /v1/query/t2a_async_query_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "async-download", "source_ids": [ "async-reference", "async-query" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "async-reference" ], "state": "unknown" }, "endpoint": "POST /v1/t2a_async_v2", "id": "text-to-speech-async", "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "async-reference" ], "state": "supported" }, { "constraints": [ "maximum_characters=1000000", "zip_member_types=txt_or_json", "json_fields=title_content_extra" ], "formats": [ "txt", "zip" ], "max_count": 1, "media_type": "binary", "min_count": 1, "role": "text_file", "source_ids": [ "async-reference", "async-guide" ], "state": "supported" } ], "source_ids": [ "async-reference", "async-guide" ], "task": "text_to_speech", "text_input": { "max": 50000, "source_ids": [ "async-reference" ], "state": "supported", "unit": "character" } } ], "conflicts": [ { "handling": "Represent direct text and file input as alternate endpoint-scoped inputs; do not require both.", "path": "capability_profiles.text-to-speech-async.reference_inputs.text_file", "source_ids": [ "async-reference" ], "summary": "The async schema marks both text and text_file_id required, while its descriptions state that they are mutually exclusive and exactly one is required." }, { "handling": "Use request-side format enums for caller capability and retain the response enum mismatch as conflicting provenance.", "path": "capability_profiles.*.delivery_profiles.*.formats", "source_ids": [ "http-reference", "websocket-reference", "async-reference" ], "summary": "Current request schemas accept MP3, PCM, FLAC, WAV, PCMU, and Opus, while response metadata enums on some surfaces still list only MP3, PCM, and FLAC." }, { "handling": "Represent single-voice and mixed-voice inputs separately and do not require the single voice when mixing.", "path": "capability_profiles.text-to-speech-http.reference_inputs.voice", "source_ids": [ "http-reference" ], "summary": "The voice_setting schema marks voice_id required, while the same reference instructs callers to leave voice_id empty when timbre_weights is used." }, { "handling": "Expose the seven model-guide emotions for Speech 2.8 and list fluent and whisper as unsupported values.", "path": "capability_profiles.*.controls.emotion", "source_ids": [ "model-guide", "http-reference", "websocket-reference", "async-reference" ], "summary": "The shared emotion enum prints fluent and whisper, but its model applicability text limits both to Speech 2.6 and explicitly says Speech 2.8 does not support whisper." }, { "handling": "Keep synchronous Opus sample-rate combinations unknown and scope the exact Opus set to the async profile.", "path": "capability_profiles.text-to-speech-http.audio_formats.opus", "source_ids": [ "http-reference", "async-reference" ], "summary": "The synchronous request lists a general sample-rate enum but does not publish the valid Opus-specific combinations; the async reference publishes a distinct Opus set including 12 kHz and 48 kHz." } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "Chinese" }, { "name": "Cantonese" }, { "name": "English" }, { "name": "Spanish" }, { "name": "French" }, { "name": "Russian" }, { "name": "German" }, { "name": "Portuguese" }, { "name": "Arabic" }, { "name": "Italian" }, { "name": "Japanese" }, { "name": "Korean" }, { "name": "Indonesian" }, { "name": "Vietnamese" }, { "name": "Turkish" }, { "name": "Dutch" }, { "name": "Ukrainian" }, { "name": "Thai" }, { "name": "Polish" }, { "name": "Romanian" }, { "name": "Greek" }, { "name": "Czech" }, { "name": "Finnish" }, { "name": "Hindi" }, { "name": "Bulgarian" }, { "name": "Danish" }, { "name": "Hebrew" }, { "name": "Malay" }, { "name": "Persian" }, { "name": "Slovak" }, { "name": "Swedish" }, { "name": "Croatian" }, { "name": "Filipino" }, { "name": "Hungarian" }, { "name": "Norwegian" }, { "name": "Slovenian" }, { "name": "Catalan" }, { "name": "Nynorsk" }, { "name": "Tamil" }, { "name": "Afrikaans" } ], "listed_count": 40, "published_label": "40 languages", "scope": "speech_output", "source_ids": [ "model-guide", "http-reference" ], "state": "supported" }, "limitations": [ { "id": "whisper-emotion-unavailable", "source_ids": [ "http-reference", "websocket-reference", "async-reference" ], "summary": "Speech 2.8 does not support the whisper emotion; fluent and whisper are limited to Speech 2.6 models." }, { "id": "latex-chinese-only", "source_ids": [ "http-reference", "websocket-reference", "async-reference" ], "summary": "LaTeX reading is available only for Chinese and forces language_boost to Chinese." }, { "id": "temporary-url-expiry", "source_ids": [ "http-reference", "async-reference", "async-query" ], "summary": "Non-streaming HTTP output URLs expire after 24 hours; asynchronous task download URLs expire after nine hours." } ], "model": { "id": "minimax/minimax-speech-2-8-hd", "lab": "MiniMax", "modality": "audio", "name": "MiniMax Speech 2.8 HD", "source_ids": [ "model-guide", "launch", "release-notes" ], "status": "available" }, "pricing": { "charges": [ { "amount": 100, "applies_when": [ "model_id=speech-2.8-hd" ], "denomination": "USD", "id": "speech-2-8-hd-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "input_character" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/guides/models-intro" }, { "id": "launch", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://www.minimax.io/news/minimax-speech-28" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/release-notes/models" }, { "id": "http-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/speech-t2a-http" }, { "id": "websocket-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/speech-t2a-websocket" }, { "id": "websocket-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/guides/speech-t2a-websocket" }, { "id": "async-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/speech-t2a-async-create" }, { "id": "async-query", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/api-reference/speech-t2a-async-query" }, { "id": "async-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/guides/speech-t2a-async" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/guides/pricing-paygo" }, { "id": "llms-docs", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://platform.minimax.io/docs/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-guide", "http-reference", "websocket-reference", "async-reference" ], "value": "speech-2.8-turbo" } ], "capability_profiles": [ { "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 128, 256 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "http-reference" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "http-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "http-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "http-reference" ] } ], "controls": [ { "default": "false", "mode": "exact_set", "name": "stream", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": 1, "max": 2, "min": 0.5, "mode": "range", "name": "speed", "source_ids": [ "http-reference" ], "state": "supported", "unit": "ratio" }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch", "source_ids": [ "http-reference" ], "state": "supported", "unit": "semitone" }, { "mode": "exact_set", "name": "emotion", "source_ids": [ "model-guide", "http-reference" ], "state": "supported", "unsupported_values": [ "fluent", "whisper" ], "values": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm" ] }, { "max": 99.99, "min": 0.01, "mode": "range", "name": "pause_duration", "source_ids": [ "http-reference" ], "state": "supported", "step": 0.01, "unit": "second" }, { "mode": "exact_set", "name": "interjection_tag", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "laughs", "chuckle", "coughs", "clear-throat", "groans", "breath", "pant", "inhale", "exhale", "gasps", "sniffs", "sighs", "snorts", "burps", "lip-smacking", "humming", "hissing", "emm", "sneezes" ] }, { "default": "false", "mode": "exact_set", "name": "text_normalization", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "latex_read", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "hex", "mode": "exact_set", "name": "output_delivery", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "hex", "url" ] }, { "default": "1", "mode": "exact_set", "name": "channel", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "1", "2" ] }, { "default": "false", "formats": [ "mp3" ], "mode": "exact_set", "name": "force_cbr", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "subtitle_enable", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "sentence", "mode": "exact_set", "name": "subtitle_type", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "sentence", "word", "word_streaming" ] }, { "default": 0, "max": 100, "min": -100, "mode": "range", "name": "voice_modify_pitch", "source_ids": [ "http-reference" ], "state": "supported", "unit": "relative" }, { "default": 0, "max": 100, "min": -100, "mode": "range", "name": "voice_modify_intensity", "source_ids": [ "http-reference" ], "state": "supported", "unit": "relative" }, { "default": 0, "max": 100, "min": -100, "mode": "range", "name": "voice_modify_timbre", "source_ids": [ "http-reference" ], "state": "supported", "unit": "relative" }, { "formats": [ "mp3", "wav", "flac" ], "mode": "exact_set", "name": "voice_sound_effect", "source_ids": [ "http-reference" ], "state": "supported", "values": [ "spacious_echo", "auditorium_echo", "lofi_telephone", "robotic" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "POST https://api.minimax.io/v1/t2a_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "hex-http-response", "source_ids": [ "http-reference" ], "state": "supported", "transport": "json_hex" }, { "default_format": "mp3", "endpoint": "POST https://api-uw.minimax.io/v1/t2a_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "low-ttfa-http-response", "source_ids": [ "http-reference" ], "state": "supported", "transport": "json_hex" }, { "default_format": "mp3", "endpoint": "POST /v1/t2a_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "temporary-url", "source_ids": [ "http-reference" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "http-reference" ], "state": "unknown" }, "endpoint": "POST /v1/t2a_v2", "frame_rate": { "source_ids": [ "model-guide" ], "state": "not_applicable" }, "id": "text-to-speech-http", "native_audio": { "source_ids": [ "model-guide" ], "state": "not_applicable" }, "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "http-reference" ], "state": "supported" }, { "constraints": [ "weight_min=1", "weight_max=100" ], "count_scope": "unique", "max_count": 4, "media_type": "voice_id", "min_count": 1, "role": "voice_mix", "source_ids": [ "http-reference" ], "state": "supported" } ], "size": { "source_ids": [ "model-guide" ], "state": "not_applicable" }, "source_ids": [ "http-reference" ], "task": "text_to_speech", "text_input": { "max": 9999, "source_ids": [ "http-reference" ], "state": "supported", "unit": "character" } }, { "controls": [ { "default": 1, "max": 2, "min": 0.5, "mode": "range", "name": "speed", "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "ratio" }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch", "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "semitone" }, { "mode": "exact_set", "name": "emotion", "source_ids": [ "model-guide", "websocket-reference" ], "state": "supported", "unsupported_values": [ "fluent", "whisper" ], "values": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm" ] }, { "default": "32000", "mode": "exact_set", "name": "output_sample_rate", "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "hertz", "values": [ "8000", "16000", "22050", "24000", "32000", "44100" ] }, { "default": "128000", "formats": [ "mp3" ], "mode": "exact_set", "name": "mp3_bitrate", "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "bit_per_second", "values": [ "32000", "64000", "128000", "256000" ] }, { "default": "1", "mode": "exact_set", "name": "channel", "source_ids": [ "websocket-reference" ], "state": "supported", "values": [ "1", "2" ] }, { "default": "false", "mode": "exact_set", "name": "continuous_sound", "source_ids": [ "websocket-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "false", "mode": "exact_set", "name": "subtitle_enable", "source_ids": [ "websocket-reference" ], "state": "supported", "values": [ "true", "false" ] }, { "default": "sentence", "mode": "exact_set", "name": "subtitle_type", "source_ids": [ "websocket-reference" ], "state": "supported", "values": [ "sentence", "word", "word_streaming" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "WSS wss://api.minimax.io/ws/v1/t2a_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "websocket-hex-audio", "source_ids": [ "websocket-reference", "websocket-guide" ], "state": "supported", "transport": "websocket" } ], "duration": { "source_ids": [ "websocket-reference" ], "state": "unknown" }, "endpoint": "WSS /ws/v1/t2a_v2", "id": "text-to-speech-websocket", "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "websocket-reference" ], "state": "supported" } ], "source_ids": [ "websocket-reference", "websocket-guide" ], "task": "text_to_speech", "text_input": { "max": 10000, "source_ids": [ "websocket-reference" ], "state": "supported", "unit": "character" } }, { "audio_formats": [ { "bitrate_mode": "exact_set", "bitrate_unit": "kilobit_per_second", "bitrates": [ 32, 64, 128, 256 ], "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "async-reference" ] }, { "family": "pcm", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "async-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 16000, 22050, 24000, 32000, 44100 ], "source_ids": [ "async-reference" ] }, { "family": "opus", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000, 12000, 16000, 24000, 48000 ], "source_ids": [ "async-reference" ] }, { "family": "ulaw", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 8000 ], "source_ids": [ "async-reference" ] } ], "controls": [ { "default": 1, "max": 2, "min": 0.5, "mode": "range", "name": "speed", "source_ids": [ "async-reference" ], "state": "supported", "unit": "ratio" }, { "default": 0, "max": 12, "min": -12, "mode": "range", "name": "pitch", "source_ids": [ "async-reference" ], "state": "supported", "unit": "semitone" }, { "mode": "exact_set", "name": "emotion", "source_ids": [ "model-guide", "async-reference" ], "state": "supported", "unsupported_values": [ "fluent", "whisper" ], "values": [ "happy", "sad", "angry", "fearful", "disgusted", "surprised", "calm" ] }, { "mode": "exact_set", "name": "interjection_tag", "source_ids": [ "async-reference" ], "state": "supported", "values": [ "laughs", "chuckle", "coughs", "clear-throat", "groans", "breath", "pant", "inhale", "exhale", "gasps", "sniffs", "sighs", "snorts", "burps", "lip-smacking", "humming", "hissing", "emm", "whistles", "sneezes", "crying", "applause" ] }, { "default": "32000", "mode": "exact_set", "name": "output_sample_rate", "source_ids": [ "async-reference" ], "state": "supported", "unit": "hertz", "values": [ "8000", "16000", "22050", "24000", "32000", "44100" ] }, { "default": "128000", "formats": [ "mp3" ], "mode": "exact_set", "name": "mp3_bitrate", "source_ids": [ "async-reference" ], "state": "supported", "unit": "bit_per_second", "values": [ "32000", "64000", "128000", "256000" ] }, { "default": "2", "mode": "exact_set", "name": "channel", "source_ids": [ "async-reference" ], "state": "supported", "values": [ "1", "2" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "GET /v1/query/t2a_async_query_v2", "formats": [ "mp3", "pcm", "flac", "wav", "pcmu_raw", "pcmu_wav", "opus" ], "id": "async-download", "source_ids": [ "async-reference", "async-query" ], "state": "supported", "transport": "temporary_url" } ], "duration": { "source_ids": [ "async-reference" ], "state": "unknown" }, "endpoint": "POST /v1/t2a_async_v2", "id": "text-to-speech-async", "reference_inputs": [ { "max_count": 1, "media_type": "voice_id", "min_count": 1, "role": "voice", "source_ids": [ "async-reference" ], "state": "supported" }, { "constraints": [ "maximum_characters=1000000", "zip_member_types=txt_or_json", "json_fields=title_content_extra" ], "formats": [ "txt", "zip" ], "max_count": 1, "media_type": "binary", "min_count": 1, "role": "text_file", "source_ids": [ "async-reference", "async-guide" ], "state": "supported" } ], "source_ids": [ "async-reference", "async-guide" ], "task": "text_to_speech", "text_input": { "max": 50000, "source_ids": [ "async-reference" ], "state": "supported", "unit": "character" } } ], "conflicts": [ { "handling": "Represent direct text and file input as alternate endpoint-scoped inputs; do not require both.", "path": "capability_profiles.text-to-speech-async.reference_inputs.text_file", "source_ids": [ "async-reference" ], "summary": "The async schema marks both text and text_file_id required, while its descriptions state that they are mutually exclusive and exactly one is required." }, { "handling": "Use request-side format enums for caller capability and retain the response enum mismatch as conflicting provenance.", "path": "capability_profiles.*.delivery_profiles.*.formats", "source_ids": [ "http-reference", "websocket-reference", "async-reference" ], "summary": "Current request schemas accept MP3, PCM, FLAC, WAV, PCMU, and Opus, while response metadata enums on some surfaces still list only MP3, PCM, and FLAC." }, { "handling": "Represent single-voice and mixed-voice inputs separately and do not require the single voice when mixing.", "path": "capability_profiles.text-to-speech-http.reference_inputs.voice", "source_ids": [ "http-reference" ], "summary": "The voice_setting schema marks voice_id required, while the same reference instructs callers to leave voice_id empty when timbre_weights is used." }, { "handling": "Expose the seven model-guide emotions for Speech 2.8 and list fluent and whisper as unsupported values.", "path": "capability_profiles.*.controls.emotion", "source_ids": [ "model-guide", "http-reference", "websocket-reference", "async-reference" ], "summary": "The shared emotion enum prints fluent and whisper, but its model applicability text limits both to Speech 2.6 and explicitly says Speech 2.8 does not support whisper." }, { "handling": "Keep synchronous Opus sample-rate combinations unknown and scope the exact Opus set to the async profile.", "path": "capability_profiles.text-to-speech-http.audio_formats.opus", "source_ids": [ "http-reference", "async-reference" ], "summary": "The synchronous request lists a general sample-rate enum but does not publish the valid Opus-specific combinations; the async reference publishes a distinct Opus set including 12 kHz and 48 kHz." } ], "documentation_state": "documented", "language_support": { "languages": [ { "name": "Chinese" }, { "name": "Cantonese" }, { "name": "English" }, { "name": "Spanish" }, { "name": "French" }, { "name": "Russian" }, { "name": "German" }, { "name": "Portuguese" }, { "name": "Arabic" }, { "name": "Italian" }, { "name": "Japanese" }, { "name": "Korean" }, { "name": "Indonesian" }, { "name": "Vietnamese" }, { "name": "Turkish" }, { "name": "Dutch" }, { "name": "Ukrainian" }, { "name": "Thai" }, { "name": "Polish" }, { "name": "Romanian" }, { "name": "Greek" }, { "name": "Czech" }, { "name": "Finnish" }, { "name": "Hindi" }, { "name": "Bulgarian" }, { "name": "Danish" }, { "name": "Hebrew" }, { "name": "Malay" }, { "name": "Persian" }, { "name": "Slovak" }, { "name": "Swedish" }, { "name": "Croatian" }, { "name": "Filipino" }, { "name": "Hungarian" }, { "name": "Norwegian" }, { "name": "Slovenian" }, { "name": "Catalan" }, { "name": "Nynorsk" }, { "name": "Tamil" }, { "name": "Afrikaans" } ], "listed_count": 40, "published_label": "40 languages", "scope": "speech_output", "source_ids": [ "model-guide", "http-reference" ], "state": "supported" }, "limitations": [ { "id": "whisper-emotion-unavailable", "source_ids": [ "http-reference", "websocket-reference", "async-reference" ], "summary": "Speech 2.8 does not support the whisper emotion; fluent and whisper are limited to Speech 2.6 models." }, { "id": "latex-chinese-only", "source_ids": [ "http-reference", "websocket-reference", "async-reference" ], "summary": "LaTeX reading is available only for Chinese and forces language_boost to Chinese." }, { "id": "temporary-url-expiry", "source_ids": [ "http-reference", "async-reference", "async-query" ], "summary": "Non-streaming HTTP output URLs expire after 24 hours; asynchronous task download URLs expire after nine hours." } ], "model": { "id": "minimax/minimax-speech-2-8-turbo", "lab": "MiniMax", "modality": "audio", "name": "MiniMax Speech 2.8 Turbo", "source_ids": [ "model-guide", "launch", "release-notes" ], "status": "available" }, "pricing": { "charges": [ { "amount": 60, "applies_when": [ "model_id=speech-2.8-turbo" ], "denomination": "USD", "id": "speech-2-8-turbo-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "input_character" } ], "source_ids": [ "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/guides/models-intro" }, { "id": "launch", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://www.minimax.io/news/minimax-speech-28" }, { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/release-notes/models" }, { "id": "http-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/speech-t2a-http" }, { "id": "websocket-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/speech-t2a-websocket" }, { "id": "websocket-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/guides/speech-t2a-websocket" }, { "id": "async-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/speech-t2a-async-create" }, { "id": "async-query", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/api-reference/speech-t2a-async-query" }, { "id": "async-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/guides/speech-t2a-async" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/guides/pricing-paygo" }, { "id": "llms-docs", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://platform.minimax.io/docs/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "resolves_to": "gpt-image-2-2026-04-21", "source_ids": [ "model-page" ], "value": "gpt-image-2" }, { "kind": "snapshot_id", "source_ids": [ "model-page" ], "value": "gpt-image-2-2026-04-21" } ], "capability_profiles": [ { "controls": [ { "default": "auto", "mode": "exact_set", "name": "quality", "source_ids": [ "image-guide" ], "state": "supported", "values": [ "auto", "low", "medium", "high" ] }, { "default": "auto", "mode": "exact_set", "name": "background", "source_ids": [ "image-guide" ], "state": "supported", "unsupported_values": [ "transparent" ], "values": [ "auto", "opaque" ] }, { "default": "auto", "mode": "exact_set", "name": "moderation", "source_ids": [ "image-guide" ], "state": "supported", "values": [ "auto", "low" ] }, { "default": 1, "max": 10, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "image-guide", "generation-reference" ], "state": "supported", "step": 1, "unit": "image" }, { "formats": [ "jpeg", "webp" ], "max": 100, "min": 0, "mode": "range", "name": "output_compression", "source_ids": [ "image-guide", "generation-reference" ], "state": "supported", "step": 1, "unit": "percent" } ], "delivery_profiles": [ { "default_format": "png", "formats": [ "png", "jpeg", "webp" ], "id": "base64-response", "source_ids": [ "image-guide" ], "state": "supported", "transport": "base64_in_response" }, { "formats": [ "png", "jpeg", "webp" ], "id": "partial-images", "max_partial_outputs": 3, "source_ids": [ "image-guide" ], "state": "supported", "transport": "streamed_events" }, { "id": "url-response", "source_ids": [ "images-reference" ], "state": "unsupported", "transport": "url" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "media_type": "audio", "role": "audio_reference", "source_ids": [ "model-page" ], "state": "unsupported" } ], "size": { "automatic": true, "default": "auto", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "3:2", "height": 1024, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1536 }, { "aspect_ratio": "2:3", "height": 1536, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "16:9", "height": 1152, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "16:9", "height": 2160, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3840 }, { "aspect_ratio": "9:16", "height": 3840, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2160 } ], "experimental_above_total_pixels": 3686400, "max_edge": 3840, "max_long_to_short_ratio": 3, "max_total_pixels": 8294400, "min_total_pixels": 655360, "mode": "range", "source_ids": [ "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "image-guide", "generation-reference" ], "task": "text_to_image", "text_input": { "max": 32000, "source_ids": [ "generation-reference" ], "state": "supported", "unit": "character" } }, { "controls": [ { "default": "auto", "mode": "exact_set", "name": "quality", "source_ids": [ "image-guide" ], "state": "supported", "values": [ "auto", "low", "medium", "high" ] }, { "default": "auto", "mode": "exact_set", "name": "background", "source_ids": [ "image-guide" ], "state": "supported", "unsupported_values": [ "transparent" ], "values": [ "auto", "opaque" ] }, { "default": "auto", "mode": "exact_set", "name": "moderation", "source_ids": [ "image-guide" ], "state": "supported", "values": [ "auto", "low" ] }, { "default": 1, "max": 10, "min": 1, "mode": "range", "name": "output_count", "source_ids": [ "image-guide", "edit-reference" ], "state": "supported", "step": 1, "unit": "image" }, { "formats": [ "jpeg", "webp" ], "max": 100, "min": 0, "mode": "range", "name": "output_compression", "source_ids": [ "image-guide", "edit-reference" ], "state": "supported", "step": 1, "unit": "percent" } ], "delivery_profiles": [ { "default_format": "png", "formats": [ "png", "jpeg", "webp" ], "id": "base64-response", "source_ids": [ "image-guide" ], "state": "supported", "transport": "base64_in_response" }, { "formats": [ "png", "jpeg", "webp" ], "id": "partial-images", "max_partial_outputs": 3, "source_ids": [ "image-guide" ], "state": "supported", "transport": "streamed_events" }, { "id": "url-response", "source_ids": [ "images-reference" ], "state": "unsupported", "transport": "url" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/images/edits", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "input_fidelity=fixed_high" ], "demonstrated_count": 4, "max_count_state": "unknown", "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "image-guide", "edit-reference" ], "state": "supported" }, { "constraints": [ "applies_to=first_image_reference", "same_format_as=image_reference", "same_dimensions_as=image_reference", "image_and_mask_file_size_less_than=50MB", "alpha_channel_required=true" ], "max_count": 1, "media_type": "image_mask", "min_count": 0, "role": "edit_mask", "source_ids": [ "image-guide" ], "state": "supported" }, { "media_type": "audio", "role": "audio_reference", "source_ids": [ "model-page" ], "state": "unsupported" } ], "size": { "automatic": true, "default": "auto", "edge_multiple": 16, "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "3:2", "height": 1024, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1536 }, { "aspect_ratio": "2:3", "height": 1536, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 1024 }, { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "16:9", "height": 1152, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2048 }, { "aspect_ratio": "16:9", "height": 2160, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 3840 }, { "aspect_ratio": "9:16", "height": 3840, "source_ids": [ "image-guide" ], "unit": "pixel", "width": 2160 } ], "experimental_above_total_pixels": 3686400, "max_edge": 3840, "max_long_to_short_ratio": 3, "max_total_pixels": 8294400, "min_total_pixels": 655360, "mode": "range", "source_ids": [ "image-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "image-guide", "edit-reference" ], "task": "image_edit" } ], "conflicts": [ { "handling": "Keep registry status unknown instead of translating Default into a lifecycle claim.", "path": "model.status", "source_ids": [ "model-page" ], "summary": "The model page marks GPT Image 2 as Default but does not publish a GA, preview, deprecated, or discontinued lifecycle term." }, { "handling": "Record endpoint-level partial-image streaming as supported and retain the broader catalog conflict.", "path": "capability_profiles.*.delivery_profiles.partial-images", "source_ids": [ "model-page", "image-guide" ], "summary": "The model page says streaming is not supported, while the image guide gives direct GPT Image 2 Image API streaming examples." }, { "handling": "Keep the model-specific maximum unknown and record four only as a demonstrated count.", "path": "capability_profiles.image-edit.reference_inputs.image_reference.max_count", "source_ids": [ "image-guide", "edit-reference" ], "summary": "The generic edit reference says GPT image models accept up to sixteen images but currently omits GPT Image 2 from its model enum; the current guide demonstrates four GPT Image 2 inputs." }, { "handling": "Store the orientation-neutral edge, divisibility, pixel-count, and ratio constraints from the model guide.", "path": "capability_profiles.*.size", "source_ids": [ "image-guide", "generation-reference" ], "summary": "The generated reference calls 3840x2160 the maximum, while the guide also lists 2160x3840." }, { "handling": "Omit the default from both profiles until the endpoint references agree.", "path": "capability_profiles.*.controls.output_compression.default", "source_ids": [ "generation-reference", "edit-reference" ], "summary": "The generation reference states a default of 100, while the edit reference omits a default for the same parameter." } ], "documentation_state": "documented", "language_support": { "scope": "prompt_input", "source_ids": [ "model-page", "image-guide" ], "state": "unknown" }, "limitations": [ { "id": "latency", "source_ids": [ "image-guide" ], "summary": "Complex prompts may require as much as two minutes of processing." }, { "id": "text-placement", "source_ids": [ "image-guide" ], "summary": "Precise text placement and clarity can remain difficult." }, { "id": "character-consistency", "source_ids": [ "image-guide" ], "summary": "Recurring characters or brand elements may not remain visually consistent across generations." }, { "id": "composition-control", "source_ids": [ "image-guide" ], "summary": "Precisely placing elements in structured or layout-sensitive compositions may be difficult." } ], "model": { "id": "openai/gpt-image-2", "lab": "OpenAI", "modality": "image", "name": "GPT Image 2", "source_ids": [ "model-page" ], "status": "unknown" }, "pricing": { "charges": [ { "amount": 5, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_input_token" }, { "amount": 1.25, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-cached-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "cached_text_input_token" }, { "amount": 8, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-image-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "image_input_token" }, { "amount": 2, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-cached-image-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "cached_image_input_token" }, { "amount": 30, "applies_when": [ "service=standard" ], "denomination": "USD", "id": "standard-image-output", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 2.5, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "text_input_token" }, { "amount": 0.625, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-cached-text-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "cached_text_input_token" }, { "amount": 4, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-image-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "image_input_token" }, { "amount": 1, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-cached-image-input", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "cached_image_input_token" }, { "amount": 15, "applies_when": [ "service=batch" ], "denomination": "USD", "id": "batch-image-output", "kind": "metered", "per": 1000000, "source_ids": [ "pricing" ], "state": "known", "unit": "image_output_token" }, { "amount": 100, "applies_when": [ "delivery=partial-images" ], "denomination": "image_output_token", "id": "partial-image-usage", "kind": "usage_increment", "per": 1, "source_ids": [ "image-guide" ], "state": "known", "unit": "partial_image" }, { "amount": 0.006, "applies_when": [ "service=standard", "quality=low", "size=1024x1024" ], "denomination": "USD", "id": "estimated-low-1024x1024", "kind": "estimate", "per": 1, "qualifier": "output_only_estimate; input token charges are additional", "source_ids": [ "image-guide" ], "state": "known", "unit": "output_image" }, { "amount": 0.005, "applies_when": [ "service=standard", "quality=low", "size=1024x1536" ], "denomination": "USD", "id": "estimated-low-1024x1536", "kind": "estimate", "per": 1, "qualifier": "output_only_estimate; input token charges are additional", "source_ids": [ "image-guide" ], "state": "known", "unit": "output_image" }, { "amount": 0.005, "applies_when": [ "service=standard", "quality=low", "size=1536x1024" ], "denomination": "USD", "id": "estimated-low-1536x1024", "kind": "estimate", "per": 1, "qualifier": "output_only_estimate; input token charges are additional", "source_ids": [ "image-guide" ], "state": "known", "unit": "output_image" }, { "amount": 0.053, "applies_when": [ "service=standard", "quality=medium", "size=1024x1024" ], "denomination": "USD", "id": "estimated-medium-1024x1024", "kind": "estimate", "per": 1, "qualifier": "output_only_estimate; input token charges are additional", "source_ids": [ "image-guide" ], "state": "known", "unit": "output_image" }, { "amount": 0.041, "applies_when": [ "service=standard", "quality=medium", "size=1024x1536" ], "denomination": "USD", "id": "estimated-medium-1024x1536", "kind": "estimate", "per": 1, "qualifier": "output_only_estimate; input token charges are additional", "source_ids": [ "image-guide" ], "state": "known", "unit": "output_image" }, { "amount": 0.041, "applies_when": [ "service=standard", "quality=medium", "size=1536x1024" ], "denomination": "USD", "id": "estimated-medium-1536x1024", "kind": "estimate", "per": 1, "qualifier": "output_only_estimate; input token charges are additional", "source_ids": [ "image-guide" ], "state": "known", "unit": "output_image" }, { "amount": 0.211, "applies_when": [ "service=standard", "quality=high", "size=1024x1024" ], "denomination": "USD", "id": "estimated-high-1024x1024", "kind": "estimate", "per": 1, "qualifier": "output_only_estimate; input token charges are additional", "source_ids": [ "image-guide" ], "state": "known", "unit": "output_image" }, { "amount": 0.165, "applies_when": [ "service=standard", "quality=high", "size=1024x1536" ], "denomination": "USD", "id": "estimated-high-1024x1536", "kind": "estimate", "per": 1, "qualifier": "output_only_estimate; input token charges are additional", "source_ids": [ "image-guide" ], "state": "known", "unit": "output_image" }, { "amount": 0.165, "applies_when": [ "service=standard", "quality=high", "size=1536x1024" ], "denomination": "USD", "id": "estimated-high-1536x1024", "kind": "estimate", "per": 1, "qualifier": "output_only_estimate; input token charges are additional", "source_ids": [ "image-guide" ], "state": "known", "unit": "output_image" } ], "source_ids": [ "pricing", "image-guide" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://developers.openai.com/api/docs/models/gpt-image-2" }, { "id": "image-guide", "kind": "documentation", "retrieved_on": "2026-08-09", "url": "https://developers.openai.com/api/docs/guides/image-generation" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-09", "url": "https://developers.openai.com/api/docs/pricing" }, { "id": "generation-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://developers.openai.com/api/reference/resources/images/methods/generate" }, { "id": "edit-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://developers.openai.com/api/reference/resources/images/methods/edit" }, { "id": "images-reference", "kind": "api_reference", "retrieved_on": "2026-08-09", "url": "https://developers.openai.com/api/reference/resources/images" } ] }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-catalog", "api-reference", "api-changelog" ], "value": "aleph2" }, { "kind": "model_id", "resolves_to": "aleph2", "source_ids": [ "api-changelog" ], "value": "aleph2_alpha" } ], "capability_profiles": [ { "api_mode": "aleph2", "controls": [ { "max": 4294967295, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "step": 1 }, { "mode": "exact_set", "name": "target_aspect_ratio", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "16:9", "4:3", "3:2", "1:1", "2:3", "3:4", "9:16", "21:9" ] }, { "mode": "exact_set", "name": "public_figure_threshold", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "auto", "low" ] } ], "delivery_profiles": [ { "endpoint": "GET /v1/tasks/{id}", "id": "task-output-url", "source_ids": [ "output-guide" ], "state": "supported", "transport": "ephemeral_url" } ], "duration": { "source_ids": [ "api-reference", "input-guide" ], "state": "unknown" }, "endpoint": "POST /v1/video_to_video", "frame_rate": { "source_ids": [ "api-reference", "input-guide" ], "state": "unknown" }, "id": "api-video-edit", "native_audio": { "source_ids": [ "api-reference", "product-page" ], "state": "unknown" }, "reference_inputs": [ { "constraints": [ "minimum_duration=2_seconds", "maximum_input_frame_rate=30_fps", "output_resolution=preserve_input_up_to_1080p", "https_url_max_bytes=33554432", "base64_data_uri_max_encoded_bytes=16777216", "runway_uri_min_bytes=512", "runway_uri_max_bytes=209715200", "https_url_max_characters=2048", "https_url_host=domain_only", "https_url_head_request=required", "https_url_content_headers=required", "https_url_redirects=unsupported" ], "duration_unit": "second", "encodings": [ "https_url", "base64_data_uri", "runway_uri" ], "formats": [ "mp4", "mov", "mkv", "webm", "3gp", "ogv", "avi", "flv", "mpg", "mpeg" ], "max_count": 1, "max_duration": 30, "media_type": "video", "min_count": 1, "role": "start_video", "source_ids": [ "api-reference", "input-guide", "api-changelog", "product-page" ], "state": "supported" }, { "constraints": [ "timestamp_mode=absolute_seconds_or_fraction", "absolute_seconds_min=0", "absolute_seconds_max=30", "fraction_min=0", "fraction_max=1", "edit_window_bounds=whole_seconds", "edit_window_end=exclusive", "all_keyframes_edit_window_consistency=required", "https_url_max_bytes=16777216", "base64_data_uri_max_encoded_bytes=5242880", "runway_uri_min_bytes=512", "runway_uri_max_bytes=209715200", "gif=unsupported" ], "encodings": [ "https_url", "base64_data_uri", "runway_uri" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 5, "media_type": "image", "min_count": 1, "role": "keyframe_sequence", "source_ids": [ "api-reference", "input-guide", "api-changelog" ], "state": "supported" } ], "size": { "source_ids": [ "input-guide", "product-page" ], "state": "unknown" }, "source_ids": [ "model-catalog", "api-reference", "api-changelog" ], "task": "video_edit", "text_input": { "max": 1000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "utf16_code_unit" } } ], "conflicts": [ { "handling": "Keep structured output size unknown and preserve the exact relationship on the start-video reference constraint.", "path": "capability_profiles.api-video-edit.size", "source_ids": [ "input-guide", "product-page" ], "summary": "Runway says Aleph 2.0 preserves the input resolution up to 1080p, but the registry's size schema cannot encode a relational preserve-input constraint as a legal output-size set or numeric range." } ], "documentation_state": "documented", "model": { "id": "runway/aleph-2-0", "lab": "Runway", "modality": "video", "name": "Aleph 2.0", "source_ids": [ "model-catalog", "api-changelog", "product-page", "prompting-guide" ], "status": "available" }, "pricing": { "charges": [ { "amount": 28, "denomination": "credit", "id": "aleph2-output", "kind": "metered", "per": 1, "profile_id": "api-video-edit", "qualifier": "Runway publishes a minimum charge of 56 credits per generation.", "source_ids": [ "api-pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.01, "applies_when": [ "channel=developer_api" ], "denomination": "USD", "id": "api-credit-purchase", "kind": "metered", "per": 1, "qualifier": "Developer API credits; sales tax may apply.", "source_ids": [ "api-pricing", "api-setup" ], "state": "known", "unit": "credit" } ], "source_ids": [ "api-pricing", "api-setup" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-catalog", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/guides/models/" }, { "id": "api-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/api/" }, { "id": "input-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/assets/inputs/" }, { "id": "output-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/assets/outputs/" }, { "id": "api-pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/guides/pricing/" }, { "id": "api-changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/api-details/api_changelog/" }, { "id": "api-setup", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/guides/using-the-api/" }, { "id": "product-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://runway.com/product/aleph-2" }, { "id": "prompting-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://help.runwayml.com/hc/en-us/articles/52150503729171-Aleph-2-0-Prompting-Guide" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-catalog", "api-reference" ], "value": "gen4.5" } ], "capability_profiles": [ { "api_mode": "gen4.5", "controls": [ { "max": 10, "min": 2, "mode": "range", "name": "duration", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "second" }, { "mode": "exact_set", "name": "ratio", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "1280:720", "720:1280" ] }, { "max": 4294967295, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "step": 1 }, { "mode": "exact_set", "name": "public_figure_threshold", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "auto", "low" ] } ], "delivery_profiles": [ { "endpoint": "GET /v1/tasks/{id}", "id": "task-output-url", "source_ids": [ "output-guide" ], "state": "supported", "transport": "ephemeral_url" } ], "duration": { "max": 10, "min": 2, "mode": "range", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/text_to_video", "frame_rate": { "source_ids": [ "api-reference" ], "state": "unknown" }, "id": "api-text-to-video", "native_audio": { "source_ids": [ "api-reference", "model-guide", "gwm-research" ], "state": "unknown" }, "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "api-reference", "model-guide" ], "unit": "pixel", "width": 1280 } ], "id": "1280:720", "source_ids": [ "api-reference", "model-guide" ] }, { "aspect_ratios": [ "9:16" ], "examples": [ { "aspect_ratio": "9:16", "height": 1280, "source_ids": [ "api-reference", "model-guide" ], "unit": "pixel", "width": 720 } ], "id": "720:1280", "source_ids": [ "api-reference", "model-guide" ] } ], "source_ids": [ "api-reference", "model-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "api-reference", "model-catalog" ], "task": "text_to_video", "text_input": { "max": 1000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "utf16_code_unit" } }, { "api_mode": "gen4.5", "controls": [ { "max": 10, "min": 2, "mode": "range", "name": "duration", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "second" }, { "mode": "exact_set", "name": "ratio", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "1280:720", "720:1280", "1104:832", "960:960", "832:1104", "1584:672" ] }, { "max": 4294967295, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "step": 1 }, { "mode": "exact_set", "name": "public_figure_threshold", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "auto", "low" ] } ], "delivery_profiles": [ { "endpoint": "GET /v1/tasks/{id}", "id": "task-output-url", "source_ids": [ "output-guide" ], "state": "supported", "transport": "ephemeral_url" } ], "duration": { "max": 10, "min": 2, "mode": "range", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/image_to_video", "frame_rate": { "source_ids": [ "api-reference" ], "state": "unknown" }, "id": "api-image-to-video", "native_audio": { "source_ids": [ "api-reference", "model-guide", "gwm-research" ], "state": "unknown" }, "reference_inputs": [ { "constraints": [ "input_aspect_ratio_min=0.5", "input_aspect_ratio_max=2.0", "https_url_max_bytes=16777216", "base64_data_uri_max_encoded_bytes=5242880", "runway_uri_min_bytes=512", "runway_uri_max_bytes=209715200", "https_url_max_characters=2048", "https_url_host=domain_only", "https_url_head_request=required", "https_url_content_headers=required", "https_url_redirects=unsupported", "gif=unsupported" ], "encodings": [ "https_url", "base64_data_uri", "runway_uri" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "api-reference", "input-guide" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "api-reference", "model-guide" ], "unit": "pixel", "width": 1280 } ], "id": "1280:720", "source_ids": [ "api-reference", "model-guide" ] }, { "aspect_ratios": [ "9:16" ], "examples": [ { "aspect_ratio": "9:16", "height": 1280, "source_ids": [ "api-reference", "model-guide" ], "unit": "pixel", "width": 720 } ], "id": "720:1280", "source_ids": [ "api-reference", "model-guide" ] }, { "aspect_ratios": [ "4:3" ], "examples": [ { "aspect_ratio": "4:3", "height": 832, "source_ids": [ "api-reference", "model-guide" ], "unit": "pixel", "width": 1104 } ], "id": "1104:832", "source_ids": [ "api-reference", "model-guide" ] }, { "aspect_ratios": [ "1:1" ], "examples": [ { "aspect_ratio": "1:1", "height": 960, "source_ids": [ "api-reference", "model-guide" ], "unit": "pixel", "width": 960 } ], "id": "960:960", "source_ids": [ "api-reference", "model-guide" ] }, { "aspect_ratios": [ "3:4" ], "examples": [ { "aspect_ratio": "3:4", "height": 1104, "source_ids": [ "api-reference", "model-guide" ], "unit": "pixel", "width": 832 } ], "id": "832:1104", "source_ids": [ "api-reference", "model-guide" ] }, { "aspect_ratios": [ "21:9" ], "examples": [ { "aspect_ratio": "21:9", "height": 672, "source_ids": [ "api-reference", "model-guide" ], "unit": "pixel", "width": 1584 } ], "id": "1584:672", "source_ids": [ "api-reference", "model-guide" ] } ], "source_ids": [ "api-reference", "model-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "api-reference", "model-catalog" ], "task": "image_to_video", "text_input": { "max": 1000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "utf16_code_unit" } }, { "duration": { "max": 10, "min": 2, "mode": "range", "source_ids": [ "model-guide" ], "state": "supported", "step": 1, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24, 25 ] }, "id": "web-text-to-video", "native_audio": { "source_ids": [ "model-guide", "gwm-research" ], "state": "unknown" }, "size": { "mode": "exact_set", "options": [ { "id": "720p", "label": "720p", "source_ids": [ "model-guide" ] } ], "source_ids": [ "model-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-guide" ], "task": "text_to_video" }, { "duration": { "max": 10, "min": 2, "mode": "range", "source_ids": [ "model-guide" ], "state": "supported", "step": 1, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24, 25 ] }, "id": "web-image-to-video", "native_audio": { "source_ids": [ "model-guide", "gwm-research" ], "state": "unknown" }, "reference_inputs": [ { "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "model-guide" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "id": "720p", "label": "720p", "source_ids": [ "model-guide" ] } ], "source_ids": [ "model-guide" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-guide" ], "task": "image_to_video" } ], "conflicts": [ { "handling": "Use the six values accepted by the callable endpoint and retain 672:1584 only as conflicting provenance.", "path": "capability_profiles.api-image-to-video.size.options", "source_ids": [ "api-reference", "input-guide" ], "summary": "The current image-to-video endpoint enum lists six sizes, while Runway's separate input guide additionally lists portrait 672:1584." }, { "handling": "Keep native audio unknown for the currently documented API and web profiles until a serving surface publishes an unambiguous availability contract.", "path": "capability_profiles.*.native_audio.state", "source_ids": [ "gwm-research", "model-guide", "api-reference" ], "summary": "Runway's GWM-1 research announcement says Gen-4.5 supports native audio generation and editing, while the current public model guide and API contract expose no Gen-4.5 audio control and describe the newer capabilities as coming to the web product." } ], "documentation_state": "documented", "limitations": [ { "id": "causal-reasoning", "source_ids": [ "gen45-research" ], "summary": "Runway documents cases where an effect can appear before its cause." }, { "id": "object-permanence", "source_ids": [ "gen45-research" ], "summary": "Runway documents that objects can disappear or appear unexpectedly across frames." }, { "id": "success-bias", "source_ids": [ "gen45-research" ], "summary": "Runway documents a bias toward attempted actions succeeding." }, { "id": "static-shots", "source_ids": [ "camera-guide" ], "summary": "Runway says truly static shots can be challenging, particularly establishing shots and wide landscapes." } ], "model": { "id": "runway/gen-4-5", "lab": "Runway", "modality": "video", "name": "Gen-4.5", "source_ids": [ "model-catalog", "api-changelog", "model-guide" ], "status": "available" }, "pricing": { "charges": [ { "amount": 12, "denomination": "credit", "id": "gen45-output", "kind": "metered", "per": 1, "source_ids": [ "api-pricing", "model-guide" ], "state": "known", "unit": "output_second" }, { "amount": 0.01, "applies_when": [ "channel=developer_api" ], "denomination": "USD", "id": "api-credit-purchase", "kind": "metered", "per": 1, "qualifier": "Developer API credits; minimum purchase is USD 10 and sales tax may apply.", "source_ids": [ "api-pricing", "api-setup" ], "state": "known", "unit": "credit" } ], "source_ids": [ "api-pricing", "model-guide", "api-setup" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-catalog", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.dev.runwayml.com/guides/models/" }, { "id": "api-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.dev.runwayml.com/api/" }, { "id": "input-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.dev.runwayml.com/assets/inputs/" }, { "id": "output-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.dev.runwayml.com/assets/outputs/" }, { "id": "api-pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://docs.dev.runwayml.com/guides/pricing/" }, { "id": "api-changelog", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://docs.dev.runwayml.com/api-details/api_changelog/" }, { "id": "api-setup", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.dev.runwayml.com/guides/using-the-api/" }, { "id": "api-versioning", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.dev.runwayml.com/api-details/versioning/" }, { "id": "model-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.runwayml.com/hc/en-us/articles/46974685288467-Creating-with-Gen-4-5" }, { "id": "camera-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://help.runwayml.com/hc/en-us/articles/46749315925395-Camera-Terms-Prompts-Examples" }, { "id": "gen45-research", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://runwayml.com/research/introducing-runway-gen-4.5" }, { "id": "gwm-research", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://runwayml.com/research/introducing-runway-gwm-1" }, { "id": "runway-changelog", "kind": "changelog", "retrieved_on": "2026-08-10", "url": "https://runwayml.com/changelog" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-catalog", "api-reference", "api-pricing" ], "value": "gen4_turbo" } ], "capability_profiles": [ { "api_mode": "gen4_turbo", "controls": [ { "max": 10, "min": 2, "mode": "range", "name": "duration", "source_ids": [ "api-reference", "api-changelog" ], "state": "supported", "step": 1, "unit": "second" }, { "mode": "exact_set", "name": "ratio", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "1280:720", "720:1280", "1104:832", "960:960", "832:1104", "1584:672" ] }, { "max": 4294967295, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "step": 1 }, { "mode": "exact_set", "name": "public_figure_threshold", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "auto", "low" ] } ], "delivery_profiles": [ { "endpoint": "GET /v1/tasks/{id}", "id": "task-output-url", "source_ids": [ "output-guide" ], "state": "supported", "transport": "ephemeral_url" } ], "duration": { "max": 10, "min": 2, "mode": "range", "source_ids": [ "api-reference", "api-changelog" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/image_to_video", "frame_rate": { "source_ids": [ "api-reference" ], "state": "unknown" }, "id": "api-image-to-video", "native_audio": { "source_ids": [ "api-reference", "model-guide" ], "state": "unknown" }, "reference_inputs": [ { "constraints": [ "position=first", "input_aspect_ratio_min=0.5", "input_aspect_ratio_max=2.358", "https_url_max_bytes=16777216", "base64_data_uri_max_encoded_bytes=5242880", "runway_uri_min_bytes=512", "runway_uri_max_bytes=209715200", "https_url_max_characters=2048", "https_url_host=domain_only", "https_url_head_request=required", "https_url_content_headers=required", "https_url_redirects=unsupported", "gif=unsupported" ], "encodings": [ "https_url", "base64_data_uri", "runway_uri" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "api-reference", "input-guide" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9" ], "examples": [ { "aspect_ratio": "16:9", "height": 720, "source_ids": [ "api-reference", "input-guide" ], "unit": "pixel", "width": 1280 } ], "id": "1280:720", "source_ids": [ "api-reference", "input-guide" ] }, { "aspect_ratios": [ "9:16" ], "examples": [ { "aspect_ratio": "9:16", "height": 1280, "source_ids": [ "api-reference", "input-guide" ], "unit": "pixel", "width": 720 } ], "id": "720:1280", "source_ids": [ "api-reference", "input-guide" ] }, { "aspect_ratios": [ "4:3" ], "examples": [ { "aspect_ratio": "4:3", "height": 832, "source_ids": [ "api-reference", "input-guide" ], "unit": "pixel", "width": 1104 } ], "id": "1104:832", "source_ids": [ "api-reference", "input-guide" ] }, { "aspect_ratios": [ "1:1" ], "examples": [ { "aspect_ratio": "1:1", "height": 960, "source_ids": [ "api-reference", "input-guide" ], "unit": "pixel", "width": 960 } ], "id": "960:960", "source_ids": [ "api-reference", "input-guide" ] }, { "aspect_ratios": [ "3:4" ], "examples": [ { "aspect_ratio": "3:4", "height": 1104, "source_ids": [ "api-reference", "input-guide" ], "unit": "pixel", "width": 832 } ], "id": "832:1104", "source_ids": [ "api-reference", "input-guide" ] }, { "aspect_ratios": [ "21:9" ], "examples": [ { "aspect_ratio": "21:9", "height": 672, "source_ids": [ "api-reference", "input-guide" ], "unit": "pixel", "width": 1584 } ], "id": "1584:672", "source_ids": [ "api-reference", "input-guide" ] } ], "source_ids": [ "api-reference", "input-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "model-catalog", "api-reference" ], "task": "image_to_video", "text_input": { "max": 1000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "utf16_code_unit" } }, { "duration": { "max": 10, "min": 5, "mode": "range", "source_ids": [ "model-guide" ], "state": "supported", "step": 5, "unit": "second" }, "frame_rate": { "mode": "exact_set", "source_ids": [ "model-guide" ], "state": "supported", "unit": "frame_per_second", "values": [ 24 ] }, "id": "web-image-to-video", "native_audio": { "source_ids": [ "model-guide" ], "state": "unknown" }, "reference_inputs": [ { "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "model-guide" ], "state": "supported" } ], "size": { "mode": "exact_set", "options": [ { "aspect_ratios": [ "16:9" ], "id": "1280:720", "source_ids": [ "model-guide" ] }, { "aspect_ratios": [ "9:16" ], "id": "720:1280", "source_ids": [ "model-guide" ] }, { "aspect_ratios": [ "1:1" ], "id": "960:960", "source_ids": [ "model-guide" ] }, { "aspect_ratios": [ "4:3" ], "id": "1104:832", "source_ids": [ "model-guide" ] }, { "aspect_ratios": [ "3:4" ], "id": "832:1104", "source_ids": [ "model-guide" ] }, { "aspect_ratios": [ "21:9" ], "id": "1584:672", "source_ids": [ "model-guide" ] } ], "source_ids": [ "model-guide" ], "state": "supported", "unit": "pixel" }, "source_ids": [ "model-guide" ], "task": "image_to_video", "text_input": { "max": 1000, "source_ids": [ "model-guide" ], "state": "supported", "unit": "character" } } ], "conflicts": [ { "handling": "Keep the flexible range on the API profile and the two web choices on the separate web profile.", "path": "capability_profiles.*.duration", "source_ids": [ "api-reference", "api-changelog", "model-guide" ], "summary": "The current API reference and October 2025 changelog permit every integer duration from two through ten seconds, while the web-product guide still lists only five- and ten-second outputs." } ], "documentation_state": "documented", "model": { "id": "runway/gen-4-turbo", "lab": "Runway", "modality": "video", "name": "Gen-4 Turbo", "source_ids": [ "model-catalog", "api-reference", "api-changelog", "model-guide" ], "status": "available" }, "pricing": { "charges": [ { "amount": 5, "denomination": "credit", "id": "gen4-turbo-output", "kind": "metered", "per": 1, "source_ids": [ "api-pricing", "model-guide" ], "state": "known", "unit": "output_second" }, { "amount": 0.01, "applies_when": [ "channel=developer_api" ], "denomination": "USD", "id": "api-credit-purchase", "kind": "metered", "per": 1, "qualifier": "Developer API credits; sales tax may apply.", "source_ids": [ "api-pricing", "api-setup" ], "state": "known", "unit": "credit" } ], "source_ids": [ "api-pricing", "model-guide", "api-setup" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-catalog", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/guides/models/" }, { "id": "api-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/api/" }, { "id": "input-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/assets/inputs/" }, { "id": "output-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/assets/outputs/" }, { "id": "api-pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/guides/pricing/" }, { "id": "api-changelog", "kind": "changelog", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/api-details/api_changelog/" }, { "id": "api-setup", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.dev.runwayml.com/guides/using-the-api/" }, { "id": "model-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://help.runwayml.com/hc/en-us/articles/37327109429011-Creating-with-Gen-4-Video" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "api-reference" ], "value": "stable-audio-2.5" } ], "capability_profiles": [ { "audio_formats": [ { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference" ] } ], "controls": [ { "default": 190, "max": 190, "min": 1, "mode": "range", "name": "duration", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": 0, "max": 4294967294, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "unit": "integer" }, { "default": 8, "max": 8, "min": 4, "mode": "range", "name": "steps", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "sampling_step" }, { "default": 1, "max": 25, "min": 1, "mode": "range", "name": "cfg_scale", "source_ids": [ "api-reference" ], "state": "supported", "unit": "guidance_scale" }, { "default": "mp3", "mode": "exact_set", "name": "output_format", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "mp3", "wav" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "POST /v2beta/audio/stable-audio-2/text-to-audio", "formats": [ "mp3", "wav" ], "id": "binary-http-response", "source_ids": [ "api-reference" ], "state": "supported", "transport": "http_response" }, { "default_format": "mp3", "endpoint": "POST /v2beta/audio/stable-audio-2/text-to-audio", "formats": [ "mp3", "wav" ], "id": "base64-json-response", "source_ids": [ "api-reference" ], "state": "supported", "transport": "json_base64" } ], "duration": { "max": 190, "min": 1, "mode": "range", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v2beta/audio/stable-audio-2/text-to-audio", "frame_rate": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "id": "text-to-audio", "native_audio": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "size": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "source_ids": [ "api-reference", "prompt-guide" ], "task": "text_to_audio", "text_input": { "max": 10000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "character" } }, { "audio_formats": [ { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference" ] } ], "controls": [ { "default": 190, "max": 190, "min": 1, "mode": "range", "name": "duration", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": 0, "max": 4294967294, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "unit": "integer" }, { "default": 8, "max": 8, "min": 4, "mode": "range", "name": "steps", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "sampling_step" }, { "default": 1, "max": 25, "min": 1, "mode": "range", "name": "cfg_scale", "source_ids": [ "api-reference" ], "state": "supported", "unit": "guidance_scale" }, { "default": 1, "max": 1, "min": 0.01, "mode": "range", "name": "strength", "source_ids": [ "api-reference" ], "state": "supported", "unit": "ratio" }, { "default": "mp3", "mode": "exact_set", "name": "output_format", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "mp3", "wav" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "POST /v2beta/audio/stable-audio-2/audio-to-audio", "formats": [ "mp3", "wav" ], "id": "binary-http-response", "source_ids": [ "api-reference" ], "state": "supported", "transport": "http_response" }, { "default_format": "mp3", "endpoint": "POST /v2beta/audio/stable-audio-2/audio-to-audio", "formats": [ "mp3", "wav" ], "id": "base64-json-response", "source_ids": [ "api-reference" ], "state": "supported", "transport": "json_base64" } ], "duration": { "max": 190, "min": 1, "mode": "range", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v2beta/audio/stable-audio-2/audio-to-audio", "frame_rate": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "id": "audio-to-audio", "native_audio": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "minimum_duration_seconds=6", "maximum_request_size=50MB" ], "duration_unit": "second", "formats": [ "mp3", "wav" ], "max_count": 1, "max_duration": 190, "media_type": "audio", "min_count": 1, "role": "audio_reference", "source_ids": [ "api-reference" ], "state": "supported" } ], "size": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "source_ids": [ "api-reference", "audio-to-audio-guide" ], "task": "audio_to_audio", "text_input": { "max": 10000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "character" } }, { "audio_formats": [ { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference" ] } ], "controls": [ { "default": 190, "max": 190, "min": 1, "mode": "range", "name": "duration", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": 0, "max": 4294967294, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "unit": "integer" }, { "default": 8, "max": 8, "min": 4, "mode": "range", "name": "steps", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "sampling_step" }, { "default": 30, "max": 190, "min": 0, "mode": "range", "name": "mask_start", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": 190, "max": 190, "min": 0, "mode": "range", "name": "mask_end", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": "mp3", "mode": "exact_set", "name": "output_format", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "mp3", "wav" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "POST /v2beta/audio/stable-audio-2/inpaint", "formats": [ "mp3", "wav" ], "id": "binary-http-response", "source_ids": [ "api-reference" ], "state": "supported", "transport": "http_response" }, { "default_format": "mp3", "endpoint": "POST /v2beta/audio/stable-audio-2/inpaint", "formats": [ "mp3", "wav" ], "id": "base64-json-response", "source_ids": [ "api-reference" ], "state": "supported", "transport": "json_base64" } ], "duration": { "max": 190, "min": 1, "mode": "range", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v2beta/audio/stable-audio-2/inpaint", "frame_rate": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "id": "audio-inpaint", "native_audio": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "minimum_duration_seconds=6", "maximum_request_size=50MB" ], "duration_unit": "second", "formats": [ "mp3", "wav" ], "max_count": 1, "max_duration": 190, "media_type": "audio", "min_count": 1, "role": "audio_reference", "source_ids": [ "api-reference" ], "state": "supported" } ], "size": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "source_ids": [ "api-reference", "prompt-guide" ], "task": "audio_inpaint", "text_input": { "max": 10000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "character" } } ], "conflicts": [ { "handling": "Use the exact 1-to-190-second API parameter range and retain the rounded three-minute prose as conflicting provenance.", "path": "capability_profiles.*.duration", "source_ids": [ "api-reference", "pricing", "launch" ], "summary": "The model overview and pricing page describe output as up to three minutes, while the endpoint parameter tables accept output duration through 190 seconds." }, { "handling": "Expose the model-specific range and default from the parameter table and retain the applicability wording as conflicting provenance.", "path": "capability_profiles.text-to-audio.controls.cfg_scale, capability_profiles.audio-to-audio.controls.cfg_scale", "source_ids": [ "api-reference" ], "summary": "The endpoint overview says cfg_scale applies only to stable-audio-2, while the same request schema publishes a Stable Audio 2.5 default of 1." } ], "documentation_state": "documented", "limitations": [ { "id": "copyrighted-upload-restriction", "source_ids": [ "api-reference" ], "summary": "The Stability API does not allow copyrighted audio to be uploaded for audio-to-audio or inpaint requests." } ], "model": { "id": "stability-ai/stable-audio-2-5", "lab": "Stability AI", "modality": "audio", "name": "Stable Audio 2.5", "source_ids": [ "launch", "api-reference", "pricing" ], "status": "available" }, "pricing": { "charges": [ { "amount": 20, "denomination": "credit", "id": "text-to-audio-generation", "kind": "metered", "per": 1, "profile_id": "text-to-audio", "qualifier": "Flat rate per successful result; failed generations are not charged.", "source_ids": [ "pricing", "api-reference" ], "state": "known", "unit": "successful_generation" }, { "amount": 20, "denomination": "credit", "id": "audio-to-audio-generation", "kind": "metered", "per": 1, "profile_id": "audio-to-audio", "qualifier": "Flat rate per successful result; failed generations are not charged.", "source_ids": [ "pricing", "api-reference" ], "state": "known", "unit": "successful_generation" }, { "amount": 20, "denomination": "credit", "id": "audio-inpaint-generation", "kind": "metered", "per": 1, "profile_id": "audio-inpaint", "qualifier": "Flat rate per successful result; failed generations are not charged.", "source_ids": [ "pricing", "api-reference" ], "state": "known", "unit": "successful_generation" } ], "source_ids": [ "pricing", "api-reference" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "launch", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://stability.ai/news-updates/stability-ai-introduces-stable-audio-25-the-first-audio-model-built-for-enterprise-sound-production-at-scale" }, { "id": "api-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.stability.ai/docs/api-reference" }, { "id": "prompt-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://stability.ai/guides/stable-audio-25-prompt-guide" }, { "id": "audio-to-audio-guide", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://kb.stability.ai/knowledge-base/tips-for-using-the-audio-to-audio-api" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://platform.stability.ai/pricing" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "api-reference" ], "value": "stable-audio-3" } ], "capability_profiles": [ { "audio_formats": [ { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference", "release-notes" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference", "release-notes" ] } ], "controls": [ { "default": 190, "max": 380, "min": 1, "mode": "range", "name": "duration", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": 0, "max": 4294967294, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "unit": "integer" }, { "default": 8, "max": 8, "min": 4, "mode": "range", "name": "steps", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "sampling_step" }, { "default": 1, "max": 25, "min": 1, "mode": "range", "name": "cfg_scale", "source_ids": [ "api-reference" ], "state": "supported", "unit": "guidance_scale" }, { "default": "mp3", "mode": "exact_set", "name": "output_format", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "mp3", "wav" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "GET /v2beta/audio/results/{id}", "formats": [ "mp3", "wav" ], "id": "asynchronous-binary-result", "source_ids": [ "api-reference" ], "state": "supported", "transport": "async_poll" }, { "default_format": "mp3", "endpoint": "GET /v2beta/audio/results/{id}", "formats": [ "mp3", "wav" ], "id": "asynchronous-base64-result", "source_ids": [ "api-reference" ], "state": "supported", "transport": "async_poll_json_base64" } ], "duration": { "max": 380, "min": 1, "mode": "range", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v2beta/audio/stable-audio/text-to-audio", "frame_rate": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "id": "text-to-audio", "native_audio": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "size": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "source_ids": [ "api-reference", "release-notes" ], "task": "text_to_audio", "text_input": { "max": 10000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "character" } }, { "audio_formats": [ { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference", "release-notes" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference", "release-notes" ] } ], "controls": [ { "default": 190, "max": 380, "min": 1, "mode": "range", "name": "duration", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": 0, "max": 4294967294, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "unit": "integer" }, { "default": 8, "max": 8, "min": 4, "mode": "range", "name": "steps", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "sampling_step" }, { "default": 1, "max": 25, "min": 1, "mode": "range", "name": "cfg_scale", "source_ids": [ "api-reference" ], "state": "supported", "unit": "guidance_scale" }, { "default": 1, "max": 1, "min": 0, "mode": "range", "name": "strength", "source_ids": [ "api-reference" ], "state": "supported", "unit": "ratio" }, { "default": "mp3", "mode": "exact_set", "name": "output_format", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "mp3", "wav" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "GET /v2beta/audio/results/{id}", "formats": [ "mp3", "wav" ], "id": "asynchronous-binary-result", "source_ids": [ "api-reference" ], "state": "supported", "transport": "async_poll" }, { "default_format": "mp3", "endpoint": "GET /v2beta/audio/results/{id}", "formats": [ "mp3", "wav" ], "id": "asynchronous-base64-result", "source_ids": [ "api-reference" ], "state": "supported", "transport": "async_poll_json_base64" } ], "duration": { "max": 380, "min": 1, "mode": "range", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v2beta/audio/stable-audio/audio-to-audio", "frame_rate": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "id": "audio-to-audio", "native_audio": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "minimum_duration_seconds=6", "maximum_request_size=100MB" ], "duration_unit": "second", "formats": [ "mp3", "wav" ], "max_count": 1, "max_duration": 380, "media_type": "audio", "min_count": 1, "role": "audio_reference", "source_ids": [ "api-reference" ], "state": "supported" } ], "size": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "source_ids": [ "api-reference", "release-notes" ], "task": "audio_to_audio", "text_input": { "max": 10000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "character" } }, { "audio_formats": [ { "family": "mp3", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference", "release-notes" ] }, { "family": "wav", "sample_rate_mode": "exact_set", "sample_rate_unit": "hertz", "sample_rates": [ 44100 ], "source_ids": [ "api-reference", "release-notes" ] } ], "controls": [ { "default": 190, "max": 380, "min": 1, "mode": "range", "name": "duration", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": 0, "max": 4294967294, "min": 0, "mode": "range", "name": "seed", "source_ids": [ "api-reference" ], "state": "supported", "unit": "integer" }, { "default": 8, "max": 8, "min": 4, "mode": "range", "name": "steps", "source_ids": [ "api-reference" ], "state": "supported", "step": 1, "unit": "sampling_step" }, { "default": 1, "max": 25, "min": 1, "mode": "range", "name": "cfg_scale", "source_ids": [ "api-reference" ], "state": "supported", "unit": "guidance_scale" }, { "default": 30, "max": 380, "min": 0, "mode": "range", "name": "mask_start", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": 380, "max": 380, "min": 0, "mode": "range", "name": "mask_end", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, { "default": "mp3", "mode": "exact_set", "name": "output_format", "source_ids": [ "api-reference" ], "state": "supported", "values": [ "mp3", "wav" ] } ], "delivery_profiles": [ { "default_format": "mp3", "endpoint": "GET /v2beta/audio/results/{id}", "formats": [ "mp3", "wav" ], "id": "asynchronous-binary-result", "source_ids": [ "api-reference" ], "state": "supported", "transport": "async_poll" }, { "default_format": "mp3", "endpoint": "GET /v2beta/audio/results/{id}", "formats": [ "mp3", "wav" ], "id": "asynchronous-base64-result", "source_ids": [ "api-reference" ], "state": "supported", "transport": "async_poll_json_base64" } ], "duration": { "max": 380, "min": 1, "mode": "range", "source_ids": [ "api-reference" ], "state": "supported", "unit": "second" }, "endpoint": "POST /v2beta/audio/stable-audio/inpaint", "frame_rate": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "id": "audio-inpaint", "native_audio": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "minimum_duration_seconds=6", "maximum_request_size=100MB" ], "duration_unit": "second", "formats": [ "mp3", "wav" ], "max_count": 1, "max_duration": 380, "media_type": "audio", "min_count": 1, "role": "audio_reference", "source_ids": [ "api-reference" ], "state": "supported" } ], "size": { "source_ids": [ "api-reference" ], "state": "not_applicable" }, "source_ids": [ "api-reference", "announcement" ], "task": "audio_inpaint", "text_input": { "max": 10000, "source_ids": [ "api-reference" ], "state": "supported", "unit": "character" } } ], "conflicts": [ { "handling": "Use the exact 1-to-380-second API parameter range and retain the rounded six-minute prose as conflicting provenance.", "path": "capability_profiles.*.duration", "source_ids": [ "api-reference", "release-notes", "announcement", "pricing" ], "summary": "The API overview, release note, and pricing page describe output as up to six minutes, while the endpoint parameter tables accept output duration through 380 seconds and the model announcement describes more than six minutes." }, { "handling": "Use the API-facing Stable Audio 3.0 name and retain Stable Audio 3.0 Large as a source-backed alias.", "path": "model.name, model.aliases", "source_ids": [ "api-reference", "release-notes", "announcement", "pricing" ], "summary": "The API reference, release note, and pricing page call the served model Stable Audio 3.0, while the launch announcement calls the API-served variant Stable Audio 3.0 Large." } ], "documentation_state": "documented", "limitations": [ { "id": "copyrighted-upload-restriction", "source_ids": [ "api-reference" ], "summary": "The Stability API does not allow copyrighted audio to be uploaded for audio-to-audio or inpaint requests." } ], "model": { "aliases": [ "Stable Audio 3.0 Large" ], "id": "stability-ai/stable-audio-3-0", "lab": "Stability AI", "modality": "audio", "name": "Stable Audio 3.0", "source_ids": [ "release-notes", "announcement", "api-reference", "pricing" ], "status": "available" }, "pricing": { "charges": [ { "amount": 26, "denomination": "credit", "id": "text-to-audio-generation", "kind": "metered", "per": 1, "profile_id": "text-to-audio", "qualifier": "Flat rate per successful generation; failed generations are not charged.", "source_ids": [ "pricing", "api-reference" ], "state": "known", "unit": "successful_generation" }, { "amount": 26, "denomination": "credit", "id": "audio-to-audio-generation", "kind": "metered", "per": 1, "profile_id": "audio-to-audio", "qualifier": "Flat rate per successful generation; failed generations are not charged.", "source_ids": [ "pricing", "api-reference" ], "state": "known", "unit": "successful_generation" }, { "amount": 26, "denomination": "credit", "id": "audio-inpaint-generation", "kind": "metered", "per": 1, "profile_id": "audio-inpaint", "qualifier": "Flat rate per successful generation; failed generations are not charged.", "source_ids": [ "pricing", "api-reference" ], "state": "known", "unit": "successful_generation" } ], "source_ids": [ "pricing", "api-reference" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "release-notes", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://platform.stability.ai/docs/release-notes" }, { "id": "announcement", "kind": "release_note", "retrieved_on": "2026-08-11", "url": "https://stability.ai/news-updates/meet-stable-audio-3-the-model-family-built-for-artistic-experimentation-with-open-weight-models" }, { "id": "api-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://platform.stability.ai/docs/api-reference" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://platform.stability.ai/pricing" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "images-reference", "llms" ], "value": "grok-imagine-image" }, { "kind": "snapshot_id", "source_ids": [ "model-page" ], "value": "grok-imagine-image-2026-03-02" } ], "capability_profiles": [ { "controls": [ { "mode": "exact_set", "name": "resolution", "source_ids": [ "model-page" ], "state": "supported", "values": [ "1k", "2k" ] }, { "name": "output_count", "source_ids": [ "images-reference", "llms" ], "state": "unknown" } ], "delivery_profiles": [ { "id": "url-response", "source_ids": [ "images-reference", "llms" ], "state": "supported", "transport": "url" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "size": { "mode": "exact_set", "options": [ { "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "model-page" ], "unit": "pixel", "width": 1024 } ], "id": "1k", "label": "1K", "source_ids": [ "model-page" ] }, { "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "model-page" ], "unit": "pixel", "width": 2048 } ], "id": "2k", "label": "2K", "source_ids": [ "model-page" ] } ], "source_ids": [ "model-page" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "model-page", "images-reference", "llms" ], "task": "text_to_image", "text_input": { "source_ids": [ "images-reference", "llms" ], "state": "unknown" } }, { "delivery_profiles": [ { "id": "url-response", "source_ids": [ "images-reference", "llms" ], "state": "supported", "transport": "url" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/images/edits", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "single-image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "encodings": [ "https_url" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "images-reference", "llms" ], "state": "supported" } ], "size": { "source_ids": [ "model-page", "images-reference", "llms" ], "state": "unknown" }, "source_ids": [ "model-page", "images-reference", "llms" ], "task": "image_edit", "text_input": { "source_ids": [ "images-reference", "llms" ], "state": "unknown" } } ], "documentation_state": "documented", "model": { "id": "xai/grok-imagine-image", "lab": "xAI", "modality": "image", "name": "Grok Imagine Image", "source_ids": [ "model-page", "images-reference" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.02, "applies_when": [ "resolution=1k_or_2k" ], "denomination": "USD", "id": "generation-output", "kind": "metered", "per": 1, "profile_id": "text-to-image", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.002, "denomination": "USD", "id": "edit-input", "kind": "metered", "per": 1, "profile_id": "single-image-edit", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0.02, "denomination": "USD", "id": "edit-output", "kind": "metered", "per": 1, "profile_id": "single-image-edit", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_image" } ], "source_ids": [ "model-page", "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-11", "url": "https://docs.x.ai/developers/models/grok-imagine-image" }, { "id": "images-reference", "kind": "api_reference", "retrieved_on": "2026-08-11", "url": "https://docs.x.ai/developers/rest-api-reference/inference/images" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-11", "url": "https://docs.x.ai/developers/pricing" }, { "id": "llms", "kind": "api_schema", "retrieved_on": "2026-08-11", "url": "https://docs.x.ai/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "images-reference", "llms" ], "value": "grok-imagine-image-quality" }, { "kind": "snapshot_id", "source_ids": [ "model-page" ], "value": "grok-imagine-image-quality-20260403" }, { "kind": "version_selector", "source_ids": [ "model-page" ], "value": "grok-imagine-image-quality-latest" }, { "kind": "version_selector", "resolves_to": "grok-imagine-image-quality", "source_ids": [ "model-page", "retirement" ], "value": "grok-imagine-image-pro" } ], "capability_profiles": [ { "controls": [ { "mode": "exact_set", "name": "resolution", "source_ids": [ "model-page", "generation-guide", "images-reference", "llms" ], "state": "supported", "values": [ "1k", "2k" ] }, { "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "generation-guide", "images-reference", "llms" ], "state": "supported", "values": [ "1:1", "3:4", "4:3", "9:16", "16:9", "2:3", "3:2", "9:19.5", "19.5:9", "9:20", "20:9", "1:2", "2:1", "auto" ] }, { "default": "url", "mode": "exact_set", "name": "response_format", "source_ids": [ "generation-guide", "images-reference", "llms" ], "state": "supported", "values": [ "url", "b64_json" ] } ], "delivery_profiles": [ { "id": "url-response", "source_ids": [ "generation-guide", "images-reference", "llms" ], "state": "supported", "transport": "url" }, { "id": "base64-response", "source_ids": [ "generation-guide", "images-reference", "llms" ], "state": "supported", "transport": "base64_in_response" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/images/generations", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "text-to-image", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "size": { "automatic": true, "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "3:4", "4:3", "9:16", "16:9", "2:3", "3:2", "9:19.5", "19.5:9", "9:20", "20:9", "1:2", "2:1" ], "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "model-page", "pricing" ], "unit": "pixel", "width": 1024 } ], "id": "1k", "label": "1K", "source_ids": [ "model-page", "generation-guide", "images-reference", "llms" ] }, { "aspect_ratios": [ "1:1", "3:4", "4:3", "9:16", "16:9", "2:3", "3:2", "9:19.5", "19.5:9", "9:20", "20:9", "1:2", "2:1" ], "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "model-page", "pricing" ], "unit": "pixel", "width": 2048 } ], "id": "2k", "label": "2K", "source_ids": [ "model-page", "generation-guide", "images-reference", "llms" ] } ], "source_ids": [ "model-page", "generation-guide", "images-reference", "llms" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "generation-guide", "images-reference", "llms" ], "task": "text_to_image", "text_input": { "source_ids": [ "generation-guide", "images-reference", "llms" ], "state": "unknown" } }, { "controls": [ { "mode": "exact_set", "name": "resolution", "source_ids": [ "model-page", "editing-guide", "images-reference", "llms" ], "state": "supported", "values": [ "1k", "2k" ] }, { "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "editing-guide", "images-reference", "llms" ], "state": "supported", "values": [ "1:1", "3:4", "4:3", "9:16", "16:9", "2:3", "3:2", "9:19.5", "19.5:9", "9:20", "20:9", "1:2", "2:1", "auto" ] }, { "default": "url", "mode": "exact_set", "name": "response_format", "source_ids": [ "editing-guide", "images-reference", "llms" ], "state": "supported", "values": [ "url", "b64_json" ] } ], "delivery_profiles": [ { "id": "url-response", "source_ids": [ "editing-guide", "images-reference", "llms" ], "state": "supported", "transport": "url" }, { "id": "base64-response", "source_ids": [ "editing-guide", "images-reference", "llms" ], "state": "supported", "transport": "base64_in_response" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/images/edits", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "single-image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "encodings": [ "https_url", "base64_data_uri", "file_id" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "image_reference", "source_ids": [ "editing-guide", "files-inputs", "images-reference", "llms" ], "state": "supported" } ], "size": { "automatic": true, "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "3:4", "4:3", "9:16", "16:9", "2:3", "3:2", "9:19.5", "19.5:9", "9:20", "20:9", "1:2", "2:1" ], "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "model-page", "pricing" ], "unit": "pixel", "width": 1024 } ], "id": "1k", "label": "1K", "source_ids": [ "model-page", "editing-guide", "images-reference", "llms" ] }, { "aspect_ratios": [ "1:1", "3:4", "4:3", "9:16", "16:9", "2:3", "3:2", "9:19.5", "19.5:9", "9:20", "20:9", "1:2", "2:1" ], "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "model-page", "pricing" ], "unit": "pixel", "width": 2048 } ], "id": "2k", "label": "2K", "source_ids": [ "model-page", "editing-guide", "images-reference", "llms" ] } ], "source_ids": [ "model-page", "editing-guide", "images-reference", "llms" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "editing-guide", "images-reference", "llms" ], "task": "image_edit", "text_input": { "source_ids": [ "editing-guide", "images-reference", "llms" ], "state": "unknown" } }, { "controls": [ { "mode": "exact_set", "name": "resolution", "source_ids": [ "model-page", "multi-editing-guide", "images-reference", "llms" ], "state": "supported", "values": [ "1k", "2k" ] }, { "default": "first_input_image_aspect_ratio", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "multi-editing-guide", "images-reference", "llms" ], "state": "supported", "values": [ "1:1", "3:4", "4:3", "9:16", "16:9", "2:3", "3:2", "9:19.5", "19.5:9", "9:20", "20:9", "1:2", "2:1", "auto" ] }, { "default": "url", "mode": "exact_set", "name": "response_format", "source_ids": [ "multi-editing-guide", "images-reference", "llms" ], "state": "supported", "values": [ "url", "b64_json" ] } ], "delivery_profiles": [ { "id": "url-response", "source_ids": [ "multi-editing-guide", "images-reference", "llms" ], "state": "supported", "transport": "url" }, { "id": "base64-response", "source_ids": [ "multi-editing-guide", "images-reference", "llms" ], "state": "supported", "transport": "base64_in_response" } ], "duration": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "endpoint": "POST /v1/images/edits", "frame_rate": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "id": "multi-image-edit", "native_audio": { "source_ids": [ "model-page" ], "state": "not_applicable" }, "reference_inputs": [ { "constraints": [ "mixed_transport_encodings_allowed=true" ], "encodings": [ "https_url", "base64_data_uri", "file_id" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 3, "media_type": "image", "min_count": 2, "role": "image_reference", "source_ids": [ "multi-editing-guide", "files-inputs", "images-reference", "llms" ], "state": "supported" } ], "size": { "automatic": true, "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "3:4", "4:3", "9:16", "16:9", "2:3", "3:2", "9:19.5", "19.5:9", "9:20", "20:9", "1:2", "2:1" ], "examples": [ { "aspect_ratio": "1:1", "height": 1024, "source_ids": [ "model-page", "pricing" ], "unit": "pixel", "width": 1024 } ], "id": "1k", "label": "1K", "source_ids": [ "model-page", "multi-editing-guide", "images-reference", "llms" ] }, { "aspect_ratios": [ "1:1", "3:4", "4:3", "9:16", "16:9", "2:3", "3:2", "9:19.5", "19.5:9", "9:20", "20:9", "1:2", "2:1" ], "examples": [ { "aspect_ratio": "1:1", "height": 2048, "source_ids": [ "model-page", "pricing" ], "unit": "pixel", "width": 2048 } ], "id": "2k", "label": "2K", "source_ids": [ "model-page", "multi-editing-guide", "images-reference", "llms" ] } ], "source_ids": [ "model-page", "multi-editing-guide", "images-reference", "llms" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "multi-editing-guide", "images-reference", "llms" ], "task": "multi_image_edit", "text_input": { "source_ids": [ "multi-editing-guide", "images-reference", "llms" ], "state": "unknown" } } ], "conflicts": [ { "handling": "Use the current model-specific pricing table and retain the lower cost-tracking example as a dated official conflict.", "path": "pricing.charges", "source_ids": [ "model-page", "pricing", "cost-tracking" ], "summary": "The current model and pricing pages publish USD 0.05 for 1K and USD 0.07 for 2K output, while an official cost-tracking example for this model reports 200000000 cost ticks, equivalent under that page's formula to USD 0.02." } ], "documentation_state": "documented", "model": { "id": "xai/grok-imagine-image-quality", "lab": "xAI", "modality": "image", "name": "Grok Imagine Image Quality", "source_ids": [ "model-page", "release" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.05, "applies_when": [ "resolution=1k" ], "denomination": "USD", "id": "generation-1k-output", "kind": "metered", "per": 1, "profile_id": "text-to-image", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.07, "applies_when": [ "resolution=2k" ], "denomination": "USD", "id": "generation-2k-output", "kind": "metered", "per": 1, "profile_id": "text-to-image", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.01, "denomination": "USD", "id": "single-edit-input", "kind": "metered", "per": 1, "profile_id": "single-image-edit", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0.05, "applies_when": [ "resolution=1k" ], "denomination": "USD", "id": "single-edit-1k-output", "kind": "metered", "per": 1, "profile_id": "single-image-edit", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.07, "applies_when": [ "resolution=2k" ], "denomination": "USD", "id": "single-edit-2k-output", "kind": "metered", "per": 1, "profile_id": "single-image-edit", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.01, "denomination": "USD", "id": "multi-edit-input", "kind": "metered", "per": 1, "profile_id": "multi-image-edit", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0.05, "applies_when": [ "resolution=1k" ], "denomination": "USD", "id": "multi-edit-1k-output", "kind": "metered", "per": 1, "profile_id": "multi-image-edit", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_image" }, { "amount": 0.07, "applies_when": [ "resolution=2k" ], "denomination": "USD", "id": "multi-edit-2k-output", "kind": "metered", "per": 1, "profile_id": "multi-image-edit", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_image" } ], "source_ids": [ "model-page", "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/models/grok-imagine-image-quality" }, { "id": "release", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://x.ai/news/grok-imagine-quality-mode" }, { "id": "generation-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/model-capabilities/images/generation" }, { "id": "editing-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/model-capabilities/images/editing" }, { "id": "multi-editing-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/model-capabilities/images/multi-image-editing" }, { "id": "images-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/rest-api-reference/inference/images" }, { "id": "files-inputs", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/model-capabilities/imagine/files/inputs" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/pricing" }, { "id": "cost-tracking", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/cost-tracking" }, { "id": "retirement", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/migration/may-15-retirement" }, { "id": "llms", "kind": "api_schema", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/llms.txt" } ], "verification": { "state": "unverified" } }, { "api_identifiers": [ { "kind": "model_id", "source_ids": [ "model-page", "llms" ], "value": "grok-imagine-video-1.5" }, { "kind": "version_selector", "resolves_to": "grok-imagine-video-1.5", "source_ids": [ "model-page" ], "value": "grok-imagine-video-1.5-preview" }, { "kind": "snapshot_id", "source_ids": [ "model-page" ], "value": "grok-imagine-video-1.5-2026-05-30" } ], "capability_profiles": [ { "api_mode": "text-to-video", "controls": [ { "default": 8, "max": 15, "min": 1, "mode": "range", "name": "duration", "source_ids": [ "llms" ], "state": "supported", "step": 1, "unit": "second" }, { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "generation-guide", "llms" ], "state": "supported", "values": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ] }, { "default": "480p", "mode": "exact_set", "name": "resolution", "source_ids": [ "generation-guide", "llms" ], "state": "supported", "values": [ "480p", "720p", "1080p" ] } ], "duration": { "max": 15, "min": 1, "mode": "range", "source_ids": [ "generation-guide", "llms" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/videos/generations", "id": "text-to-video", "native_audio": { "default": true, "source_ids": [ "generation-guide", "release" ], "state": "supported" }, "size": { "default": "480p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ], "id": "480p", "label": "Standard definition", "source_ids": [ "generation-guide", "llms" ] }, { "aspect_ratios": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ], "id": "720p", "label": "HD quality", "source_ids": [ "generation-guide", "llms" ] }, { "aspect_ratios": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ], "id": "1080p", "label": "Full HD quality", "source_ids": [ "generation-guide", "llms" ] } ], "source_ids": [ "generation-guide", "llms" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "generation-guide", "videos-reference", "llms" ], "task": "text_to_video" }, { "api_mode": "image-to-video", "controls": [ { "default": 8, "max": 15, "min": 1, "mode": "range", "name": "duration", "source_ids": [ "llms" ], "state": "supported", "step": 1, "unit": "second" }, { "default": "input_image_aspect_ratio", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "generation-guide", "llms" ], "state": "supported", "values": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ] }, { "default": "480p", "mode": "exact_set", "name": "resolution", "source_ids": [ "generation-guide", "image-to-video-guide", "llms" ], "state": "supported", "values": [ "480p", "720p", "1080p" ] } ], "duration": { "max": 15, "min": 1, "mode": "range", "source_ids": [ "generation-guide", "llms" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/videos/generations", "id": "image-to-video", "native_audio": { "default": true, "source_ids": [ "generation-guide", "release" ], "state": "supported" }, "reference_inputs": [ { "encodings": [ "https_url", "base64_data_uri", "file_id" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 1, "media_type": "image", "min_count": 1, "role": "start_image", "source_ids": [ "image-to-video-guide", "llms" ], "state": "supported" } ], "size": { "default": "480p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ], "id": "480p", "label": "Standard definition", "source_ids": [ "generation-guide", "llms" ] }, { "aspect_ratios": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ], "id": "720p", "label": "HD quality", "source_ids": [ "generation-guide", "llms" ] }, { "aspect_ratios": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ], "id": "1080p", "label": "Full HD quality", "source_ids": [ "generation-guide", "image-to-video-guide", "llms" ] } ], "source_ids": [ "generation-guide", "image-to-video-guide", "llms" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "image-to-video-guide", "generation-guide", "videos-reference", "llms" ], "task": "image_to_video" }, { "api_mode": "reference-to-video", "controls": [ { "default": 8, "max": 15, "min": 1, "mode": "range", "name": "duration", "source_ids": [ "llms" ], "state": "supported", "step": 1, "unit": "second" }, { "default": "16:9", "mode": "exact_set", "name": "aspect_ratio", "source_ids": [ "generation-guide", "llms" ], "state": "supported", "values": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ] }, { "default": "480p", "mode": "exact_set", "name": "resolution", "source_ids": [ "reference-to-video-guide", "generation-guide", "llms" ], "state": "supported", "values": [ "480p", "720p" ] } ], "duration": { "max": 15, "min": 1, "mode": "range", "source_ids": [ "reference-to-video-guide", "generation-guide", "llms" ], "state": "supported", "step": 1, "unit": "second" }, "endpoint": "POST /v1/videos/generations", "id": "reference-to-video", "native_audio": { "default": true, "source_ids": [ "generation-guide", "reference-to-video-guide", "release" ], "state": "supported" }, "reference_inputs": [ { "constraints": [ "combined_reference_min_count=1", "mutually_exclusive_with=image_to_video", "mutually_exclusive_with=video_editing" ], "encodings": [ "https_url", "base64_data_uri", "file_id" ], "formats": [ "jpeg", "png", "webp" ], "max_count": 7, "media_type": "image", "min_count": 0, "role": "image_reference", "source_ids": [ "reference-to-video-guide", "llms" ], "state": "supported" }, { "constraints": [ "preset_voice_only", "combined_reference_min_count=1", "mutually_exclusive_with=image_to_video", "mutually_exclusive_with=video_editing" ], "max_count": 3, "media_type": "voice_id", "min_count": 0, "role": "audio_reference", "source_ids": [ "reference-to-video-guide", "generation-guide", "llms" ], "state": "supported" } ], "size": { "default": "480p", "mode": "exact_set", "options": [ { "aspect_ratios": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ], "id": "480p", "label": "Standard definition", "source_ids": [ "generation-guide", "llms" ] }, { "aspect_ratios": [ "1:1", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3" ], "id": "720p", "label": "HD quality", "source_ids": [ "reference-to-video-guide", "generation-guide", "llms" ] } ], "source_ids": [ "reference-to-video-guide", "generation-guide", "llms" ], "state": "supported", "unit": "resolution_tier" }, "source_ids": [ "reference-to-video-guide", "generation-guide", "videos-reference", "llms" ], "task": "reference_to_video" } ], "documentation_state": "documented", "model": { "aliases": [ "Grok Video 1.5" ], "id": "xai/grok-imagine-video-1-5", "lab": "xAI", "modality": "video", "name": "Grok Imagine Video 1.5", "source_ids": [ "model-page", "release" ], "status": "available" }, "pricing": { "charges": [ { "amount": 0.08, "applies_when": [ "resolution=480p" ], "denomination": "USD", "id": "t2v-480p-output", "kind": "metered", "per": 1, "profile_id": "text-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.14, "applies_when": [ "resolution=720p" ], "denomination": "USD", "id": "t2v-720p-output", "kind": "metered", "per": 1, "profile_id": "text-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.25, "applies_when": [ "resolution=1080p" ], "denomination": "USD", "id": "t2v-1080p-output", "kind": "metered", "per": 1, "profile_id": "text-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.01, "denomination": "USD", "id": "i2v-image-input", "kind": "metered", "per": 1, "profile_id": "image-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0.08, "applies_when": [ "resolution=480p" ], "denomination": "USD", "id": "i2v-480p-output", "kind": "metered", "per": 1, "profile_id": "image-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.14, "applies_when": [ "resolution=720p" ], "denomination": "USD", "id": "i2v-720p-output", "kind": "metered", "per": 1, "profile_id": "image-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.25, "applies_when": [ "resolution=1080p" ], "denomination": "USD", "id": "i2v-1080p-output", "kind": "metered", "per": 1, "profile_id": "image-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.01, "denomination": "USD", "id": "r2v-image-input", "kind": "metered", "per": 1, "profile_id": "reference-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "input_image" }, { "amount": 0, "denomination": "USD", "id": "r2v-preset-voice-input", "kind": "metered", "per": 1, "profile_id": "reference-to-video", "qualifier": "included", "source_ids": [ "model-page" ], "state": "known", "unit": "preset_voice_input" }, { "amount": 0.08, "applies_when": [ "resolution=480p" ], "denomination": "USD", "id": "r2v-480p-output", "kind": "metered", "per": 1, "profile_id": "reference-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_second" }, { "amount": 0.14, "applies_when": [ "resolution=720p" ], "denomination": "USD", "id": "r2v-720p-output", "kind": "metered", "per": 1, "profile_id": "reference-to-video", "source_ids": [ "model-page", "pricing" ], "state": "known", "unit": "output_second" } ], "source_ids": [ "model-page", "pricing" ], "state": "known" }, "schema_version": 1, "sources": [ { "id": "model-page", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/models/grok-imagine-video-1.5" }, { "id": "release", "kind": "release_note", "retrieved_on": "2026-08-10", "url": "https://x.ai/news/grok-imagine-video-1-5" }, { "id": "generation-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/model-capabilities/video/generation" }, { "id": "image-to-video-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/model-capabilities/video/image-to-video" }, { "id": "reference-to-video-guide", "kind": "documentation", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/model-capabilities/video/reference-to-video" }, { "id": "videos-reference", "kind": "api_reference", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/rest-api-reference/inference/videos" }, { "id": "pricing", "kind": "pricing", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/developers/pricing" }, { "id": "llms", "kind": "api_schema", "retrieved_on": "2026-08-10", "url": "https://docs.x.ai/llms.txt" } ], "verification": { "state": "unverified" } } ], "schema_version": 1 }