changedOutput schema / properties / models / items / anyOf
Previous value: -[
- {
- "properties": {
- "aspect_ratios": {
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- "audio_requires_visual_reference": {
- "type": "boolean"
- },
- "default_aspect_ratio": {
- "type": "string"
- },
- "default_duration": {
- "anyOf": [
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
- ]
- },
- "default_quality": {
- "anyOf": [
- {
- "type": "string"
- },
- {
- "type": "null"
- }
- ]
- },
- "default_resolution": {
- "type": "string"
- },
- "durations": {
- "anyOf": [
- {
- "items": {
- "minimum": 1,
- "type": "integer"
- },
- "minItems": 1,
- "type": "array"
- },
- {
- "pattern": "^[1-9][0-9]*-[1-9][0-9]*$",
- "type": "string"
- },
- {
- "type": "null"
- }
- ],
- "description": "Allowed integer seconds: an inclusive range such as \"2-30\", or discrete values such as [4, 6, 8]; null for images."
- },
- "explicit_aspect_ratio_modes": {
- "items": {
- "enum": [
- "text_to_image",
- "image_to_image",
- "text_to_video",
- "first_frame_video",
- "first_last_frame_video",
- "multimodal_reference_video"
- ],
- "type": "string"
- },
- "type": "array"
- },
- "max_audio_references": {
- "anyOf": [
- {
- "type": "integer"
- },
- {
- "type": "null"
- }
- ],
- "description": "Model-specific audio reference limit; null means no additional model limit."
- },
- "media_type": {
- "enum": [
- "image",
- "video"
- ],
- "type": "string"
- },
- "model_id": {
- "type": "string"
- },
- "model_name": {
- "description": "Human-readable model name for display; use model_id when submitting tasks.",
- "type": "string"
- },
- "modes": {
- "items": {
- "enum": [
- "text_to_image",
- "image_to_image",
- "text_to_video",
- "first_frame_video",
- "first_last_frame_video",
- "multimodal_reference_video"
- ],
- "type": "string"
- },
- "type": "array"
- },
- "native_audio": {
- "anyOf": [
- {
- "type": "boolean"
- },
- {
- "type": "null"
- }
- ]
- },
- "qualities": {
- "anyOf": [
- {
- "items": {
- "type": "string"
- },
- "type": "array"
- },
- {
- "type": "null"
- }
- ]
- },
- "reference_types": {
- "description": "Accepted reference types for multimodal_reference_video; empty if unsupported.",
- "items": {
- "enum": [
- "image",
- "video",
- "audio"
- ],
- "type": "string"
- },
- "type": "array"
- },
- "resolutions": {
- "items": {
- "type": "string"
- },
- "type": "array"
- }
- },
- "required": [
- "model_id",
- "model_name",
- "media_type",
- "modes",
- "reference_types",
- "max_audio_references",
- "audio_requires_visual_reference",
- "resolutions",
- "default_resolution",
- "aspect_ratios",
- "default_aspect_ratio",
- "explicit_aspect_ratio_modes",
- "qualities",
- "default_quality",
- "durations",
- "default_duration",
- "native_audio"
- ],
- "type": "object"
- },
- {
- "description": "Public catalog entry, without internal provider routes or payload policies.",
- "properties": {
- "media_type": {
- "enum": [
- "image",
- "video"
- ],
- "type": "string"
- },
- "model_id": {
- "type": "string"
- },
- "model_name": {
- "description": "Human-readable model name for display; use model_id when submitting tasks.",
- "type": "string"
- },
- "modes": {
- "items": {
- "enum": [
- "text_to_image",
- "image_to_image",
- "text_to_video",
- "first_frame_video",
- "first_last_frame_video",
- "multimodal_reference_video"
- ],
- "type": "string"
- },
- "type": "array"
- }
- },
- "required": [
- "model_id",
- "model_name",
- "media_type",
- "modes"
- ],
- "type": "object"
- }
-]New value: +[
+ {
+ "properties": {
+ "aspect_ratios": {
+ "description": "Supported output aspect ratios.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "audio_requires_visual_reference": {
+ "description": "Whether audio references must accompany an image or video.",
+ "type": "boolean"
+ },
+ "default_aspect_ratio": {
+ "description": "Aspect ratio used when auto is permitted.",
+ "type": "string"
+ },
+ "default_duration": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Video duration in seconds when duration is 0; null for images."
+ },
+ "default_quality": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Quality used when omitted; null if unused."
+ },
+ "default_resolution": {
+ "description": "Resolution used when resolution is auto.",
+ "type": "string"
+ },
+ "durations": {
+ "anyOf": [
+ {
+ "items": {
+ "minimum": 1,
+ "type": "integer"
+ },
+ "minItems": 1,
+ "type": "array"
+ },
+ {
+ "pattern": "^[1-9][0-9]*-[1-9][0-9]*$",
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Allowed integer seconds: an inclusive range such as \"2-30\", or discrete values such as [4, 6, 8]; null for images."
+ },
+ "explicit_aspect_ratio_modes": {
+ "description": "Modes requiring a concrete aspect ratio. For multimodal video, applies only with image references and no video references.",
+ "items": {
+ "anyOf": [
+ {
+ "enum": [
+ "text_to_image",
+ "image_to_image",
+ "text_to_video",
+ "first_frame_video",
+ "first_last_frame_video",
+ "multimodal_reference_video"
+ ],
+ "type": "string"
+ },
+ {
+ "enum": [
+ "soundtrack",
+ "track",
+ "songextend",
+ "songremix",
+ "songedit",
+ "audiostem",
+ "text2audio",
+ "podcast"
+ ],
+ "type": "string"
+ }
+ ]
+ },
+ "type": "array"
+ },
+ "max_audio_references": {
+ "anyOf": [
+ {
+ "type": "integer"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Model-specific audio reference limit; null means no additional model limit."
+ },
+ "media_type": {
+ "description": "Output media category.",
+ "enum": [
+ "image",
+ "video",
+ "audio"
+ ],
+ "type": "string"
+ },
+ "model_id": {
+ "description": "Exact identifier for model details and tools with model selection.",
+ "type": "string"
+ },
+ "model_name": {
+ "description": "Model name to display to the user.",
+ "type": "string"
+ },
+ "modes": {
+ "description": "Supported generation or processing capabilities.",
+ "items": {
+ "anyOf": [
+ {
+ "enum": [
+ "text_to_image",
+ "image_to_image",
+ "text_to_video",
+ "first_frame_video",
+ "first_last_frame_video",
+ "multimodal_reference_video"
+ ],
+ "type": "string"
+ },
+ {
+ "enum": [
+ "soundtrack",
+ "track",
+ "songextend",
+ "songremix",
+ "songedit",
+ "audiostem",
+ "text2audio",
+ "podcast"
+ ],
+ "type": "string"
+ }
+ ]
+ },
+ "type": "array"
+ },
+ "native_audio": {
+ "anyOf": [
+ {
+ "type": "boolean"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Whether native video audio can be generated; null for images."
+ },
+ "qualities": {
+ "anyOf": [
+ {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "description": "Supported image quality options; null if unused."
+ },
+ "reference_types": {
+ "description": "Accepted reference types for multimodal_reference_video; empty if unsupported.",
+ "items": {
+ "enum": [
+ "image",
+ "video",
+ "audio"
+ ],
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "resolutions": {
+ "description": "Supported native output resolutions.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "model_id",
+ "model_name",
+ "media_type",
+ "modes",
+ "reference_types",
+ "max_audio_references",
+ "audio_requires_visual_reference",
+ "resolutions",
+ "default_resolution",
+ "aspect_ratios",
+ "default_aspect_ratio",
+ "explicit_aspect_ratio_modes",
+ "qualities",
+ "default_quality",
+ "durations",
+ "default_duration",
+ "native_audio"
+ ],
+ "type": "object"
+ },
+ {
+ "properties": {
+ "media_type": {
+ "const": "audio",
+ "default": "audio",
+ "description": "Output media category.",
+ "type": "string"
+ },
+ "model_id": {
+ "description": "Exact identifier for model details and tools with model selection.",
+ "type": "string"
+ },
+ "model_name": {
+ "description": "Model name to display to the user.",
+ "type": "string"
+ },
+ "modes": {
+ "description": "Supported generation or processing capabilities.",
+ "items": {
+ "anyOf": [
+ {
+ "enum": [
+ "text_to_image",
+ "image_to_image",
+ "text_to_video",
+ "first_frame_video",
+ "first_last_frame_video",
+ "multimodal_reference_video"
+ ],
+ "type": "string"
+ },
+ {
+ "enum": [
+ "soundtrack",
+ "track",
+ "songextend",
+ "songremix",
+ "songedit",
+ "audiostem",
+ "text2audio",
+ "podcast"
+ ],
+ "type": "string"
+ }
+ ]
+ },
+ "type": "array"
+ },
+ "operations": {
+ "description": "Supported audio operations, tool selectors and parameter guidance.",
+ "items": {
+ "additionalProperties": false,
+ "description": "Public guidance for one audio capability, without provider request paths.",
+ "properties": {
+ "default_model_id": {
+ "anyOf": [
+ {
+ "type": "string"
+ },
+ {
+ "type": "null"
+ }
+ ],
+ "default": null,
+ "description": "Model used when model selection is omitted; null for fixed-model tools."
+ },
+ "model_selection": {
+ "description": "optional: tool accepts model_id; fixed: tool selects the model.",
+ "enum": [
+ "optional",
+ "fixed"
+ ],
+ "type": "string"
+ },
+ "optional_parameters": {
+ "description": "Additional tool arguments accepted for this operation.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "parameter_notes": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Usage guidance keyed by tool argument name.",
+ "type": "object"
+ },
+ "reference_requirements": {
+ "description": "Required source media or text and confirmed input constraints.",
+ "type": "string"
+ },
+ "required_parameters": {
+ "description": "Tool arguments required for this operation.",
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "result_format": {
+ "description": "Output format: mp3 audio or zip archive.",
+ "enum": [
+ "mp3",
+ "zip"
+ ],
+ "type": "string"
+ },
+ "selector": {
+ "additionalProperties": {
+ "type": "string"
+ },
+ "description": "Tool arguments selecting this operation, such as mode or operation.",
+ "type": "object"
+ },
+ "synchronous": {
+ "description": "Whether submission usually returns a finished result; always check the returned status.",
+ "type": "boolean"
+ },
+ "task_type": {
+ "description": "Audio operation identifier.",
+ "enum": [
+ "soundtrack",
+ "track",
+ "songextend",
+ "songremix",
+ "songedit",
+ "audiostem",
+ "text2audio",
+ "podcast"
+ ],
+ "type": "string"
+ },
+ "tool_name": {
+ "description": "MCP tool that performs this operation.",
+ "type": "string"
+ }
+ },
+ "required": [
+ "task_type",
+ "tool_name",
+ "model_selection",
+ "required_parameters",
+ "parameter_notes",
+ "reference_requirements",
+ "result_format",
+ "synchronous"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "model_id",
+ "model_name",
+ "modes",
+ "operations"
+ ],
+ "type": "object"
+ },
+ {
+ "description": "Public catalog entry, without internal provider routes or payload policies.",
+ "properties": {
+ "media_type": {
+ "description": "Output media category.",
+ "enum": [
+ "image",
+ "video",
+ "audio"
+ ],
+ "type": "string"
+ },
+ "model_id": {
+ "description": "Exact identifier for model details and tools with model selection.",
+ "type": "string"
+ },
+ "model_name": {
+ "description": "Model name to display to the user.",
+ "type": "string"
+ },
+ "modes": {
+ "description": "Supported generation or processing capabilities.",
+ "items": {
+ "anyOf": [
+ {
+ "enum": [
+ "text_to_image",
+ "image_to_image",
+ "text_to_video",
+ "first_frame_video",
+ "first_last_frame_video",
+ "multimodal_reference_video"
+ ],
+ "type": "string"
+ },
+ {
+ "enum": [
+ "soundtrack",
+ "track",
+ "songextend",
+ "songremix",
+ "songedit",
+ "audiostem",
+ "text2audio",
+ "podcast"
+ ],
+ "type": "string"
+ }
+ ]
+ },
+ "type": "array"
+ }
+ },
+ "required": [
+ "model_id",
+ "model_name",
+ "media_type",
+ "modes"
+ ],
+ "type": "object"
+ }
+]
