Skip to content

ark_list_models

List configured models, limits, and cached account prices. Makes no provider calls.

Call before generation or understanding tools: their model argument accepts only the exact model_id values listed, and the server validates requests against these limits. services shows which optional services are enabled and the setting that enables a disabled one.

Requirement Value
Registration Always registered; no provider credentials required.
Execution Foreground only
Required permission No fixed per-tool scope; HTTP authentication and target-tool authorization still apply.

This site lists the full configured capability surface, not the tools enabled on your particular server. Use model discovery and job discovery to check your connection. Credentials are server configuration, never tool arguments.

Ask your connected AI client to use ark_list_models for the operation you want. The client constructs the arguments and handles tool calls. Review its proposed operation before approving anything billable. For a non-billable introduction, start with discovery without generation.

Call this tool directly. It is not a background-job target.

Exact MCP call (for developers)

The following is an MCP tool-call envelope, not a shell command. Example media URLs and identifiers must be replaced with your own accessible resources. Seedream and Seedance examples are non-billable dry runs; other provider operations may incur charges.

{
"name": "ark_list_models",
"arguments": {
"input": {}
}
}

The MCP arguments object wraps these fields as {"input": {...}}.

Field Type Required Description and constraints
kind “video”, “image”, “3d”, “understanding” or null No Filter to one model kind: video, image, 3d, or understanding. Omit to list every configured kind.; Default: null
Field Type Required Description and constraints
models array of ModelInfo Yes Configured models matching the filter.
pricing_note string or null No Why cached prices are unavailable, without credential values.; Default: null
pricing_status “live”, “unavailable” No live if a fresh catalog snapshot exists; otherwise unavailable.; Default: “unavailable”
services array of ServiceStatus Yes Enablement of each optional service.

Field types named above refer to these shared definitions. Optional/null fields, enum choices and bounds are retained in the complete schemas below. Schema validation is followed by runtime capability and security checks.

ArkListModelsInput
Field Type Required Description and constraints
kind “video”, “image”, “3d”, “understanding” or null No Filter to one model kind: video, image, 3d, or understanding. Omit to list every configured kind.; Default: null
Input schema, including the MCP wrapper
{
"$defs": {
"ArkListModelsInput": {
"description": "Input model for ``ark_list_models``.",
"properties": {
"kind": {
"anyOf": [
{
"enum": [
"video",
"image",
"3d",
"understanding"
],
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Filter to one model kind: video, image, 3d, or understanding. Omit to list every configured kind."
}
},
"type": "object"
}
},
"additionalProperties": false,
"properties": {
"input": {
"$ref": "#/$defs/ArkListModelsInput"
}
},
"required": [
"input"
],
"type": "object"
}
Output schema, including nested definitions
{
"$defs": {
"ChargeItem": {
"description": "Account-specific catalog rate.",
"properties": {
"charge_type": {
"description": "Catalog rate type, e.g. InferencePrompt, InferenceCompletion, or ToICompletion.",
"title": "Charge Type",
"type": "string"
},
"list_price": {
"description": "Published price per unit before discounts.",
"minimum": 0,
"title": "List Price",
"type": "number"
},
"price": {
"description": "Discounted account price per unit.",
"minimum": 0,
"title": "Price",
"type": "number"
},
"unit": {
"description": "Catalog billing unit: K tokens (1,000 tokens), Piece, or another unit.",
"title": "Unit",
"type": "string"
}
},
"required": [
"charge_type",
"price",
"list_price",
"unit"
],
"title": "ChargeItem",
"type": "object"
},
"ImageModelLimits": {
"description": "Per-model limits for a Seedream image model.",
"properties": {
"background_modes": {
"description": "Accepted backgrounds; 5.5 defaults to auto, older models to opaque.",
"items": {
"type": "string"
},
"title": "Background Modes",
"type": "array"
},
"custom_size_aspect_ratio_range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "number"
},
{
"type": "number"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Inclusive custom width/height ratio bounds; null if unspecified.",
"title": "Custom Size Aspect Ratio Range"
},
"custom_size_pixels_range": {
"anyOf": [
{
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Inclusive custom WIDTHxHEIGHT pixel-count bounds; null if unspecified.",
"title": "Custom Size Pixels Range"
},
"max_reference_images": {
"description": "Maximum reference images.",
"title": "Max Reference Images",
"type": "integer"
},
"output_formats": {
"description": "Accepted output formats.",
"items": {
"type": "string"
},
"title": "Output Formats",
"type": "array"
},
"prompt_optimization_modes": {
"description": "Accepted explicit prompt_optimization modes.",
"items": {
"type": "string"
},
"title": "Prompt Optimization Modes",
"type": "array"
},
"supported_sizes": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"description": "Named size tiers (5.5 default: 2K); null for provider validation.",
"title": "Supported Sizes"
},
"supports_batch": {
"description": "Accepts max_images > 1.",
"title": "Supports Batch",
"type": "boolean"
},
"supports_prompt_optimization": {
"description": "Accepts explicit prompt_optimization.",
"title": "Supports Prompt Optimization",
"type": "boolean"
},
"supports_safety_identifier": {
"description": "Accepts a hashed end-user safety_identifier.",
"title": "Supports Safety Identifier",
"type": "boolean"
},
"supports_transparent_background": {
"description": "Accepts background='transparent'.",
"title": "Supports Transparent Background",
"type": "boolean"
},
"supports_transparent_generation": {
"description": "Transparent PNGs from text-only prompts or references without alpha (5.5).",
"title": "Supports Transparent Generation",
"type": "boolean"
}
},
"required": [
"max_reference_images",
"output_formats",
"supports_batch",
"background_modes",
"prompt_optimization_modes",
"supports_safety_identifier",
"supports_transparent_background",
"supports_transparent_generation",
"supports_prompt_optimization"
],
"title": "ImageModelLimits",
"type": "object"
},
"ModelInfo": {
"description": "One configured model binding.",
"properties": {
"family": {
"description": "Logical model family.",
"title": "Family",
"type": "string"
},
"image": {
"anyOf": [
{
"$ref": "#/$defs/ImageModelLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "Limits for image models."
},
"is_default": {
"description": "Whether this model is used when `model` is omitted. For understanding models, the default for requests with audio and the default for requests without audio are both marked.",
"title": "Is Default",
"type": "boolean"
},
"kind": {
"description": "Model kind.",
"enum": [
"video",
"image",
"3d",
"understanding"
],
"title": "Kind",
"type": "string"
},
"model_id": {
"description": "Configured model ID; pass as `model` when the tool supports selection.",
"title": "Model Id",
"type": "string"
},
"pricing": {
"anyOf": [
{
"$ref": "#/$defs/ModelPricing"
},
{
"type": "null"
}
],
"default": null,
"description": "Fresh account catalog prices, or null if not cached for this model."
},
"seed3d": {
"anyOf": [
{
"$ref": "#/$defs/Seed3DModelLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "Limits for 3D models."
},
"tool": {
"description": "Tool serving this model; understanding limits describe this route.",
"title": "Tool",
"type": "string"
},
"understanding": {
"anyOf": [
{
"$ref": "#/$defs/UnderstandingModelLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "Limits for understanding models."
},
"video": {
"anyOf": [
{
"$ref": "#/$defs/VideoModelLimits"
},
{
"type": "null"
}
],
"default": null,
"description": "Limits for video models."
}
},
"required": [
"model_id",
"family",
"kind",
"is_default",
"tool"
],
"title": "ModelInfo",
"type": "object"
},
"ModelPricing": {
"description": "Cached foundation-model prices.",
"properties": {
"available": {
"description": "Whether this account has activated the model.",
"title": "Available",
"type": "boolean"
},
"catalog_name": {
"description": "Foundation model name without a trailing version date.",
"title": "Catalog Name",
"type": "string"
},
"charge_items": {
"description": "Catalog rates for this model.",
"items": {
"$ref": "#/$defs/ChargeItem"
},
"title": "Charge Items",
"type": "array"
},
"display_name": {
"description": "Human-readable model name from the catalog.",
"title": "Display Name",
"type": "string"
}
},
"required": [
"catalog_name",
"display_name",
"available"
],
"title": "ModelPricing",
"type": "object"
},
"Seed3DModelLimits": {
"description": "Per-model limits for a Seed 3D model.",
"properties": {
"file_formats": {
"description": "Accepted file_format values.",
"items": {
"type": "string"
},
"title": "File Formats",
"type": "array"
},
"max_reference_images": {
"description": "Maximum reference images per request.",
"title": "Max Reference Images",
"type": "integer"
},
"supports_seed": {
"description": "Whether a seed is accepted.",
"title": "Supports Seed",
"type": "boolean"
},
"supports_text_to_3d": {
"description": "Whether a text-only prompt is accepted.",
"title": "Supports Text To 3D",
"type": "boolean"
}
},
"required": [
"supports_text_to_3d",
"max_reference_images",
"file_formats",
"supports_seed"
],
"title": "Seed3DModelLimits",
"type": "object"
},
"ServiceStatus": {
"description": "Whether one optional service is available.",
"properties": {
"enabled": {
"description": "Whether the service's tools or models are available.",
"title": "Enabled",
"type": "boolean"
},
"reason": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Why the service is disabled, naming the env var or flag to set; never a secret value.",
"title": "Reason"
},
"service": {
"description": "Service name.",
"title": "Service",
"type": "string"
}
},
"required": [
"service",
"enabled"
],
"title": "ServiceStatus",
"type": "object"
},
"UnderstandingModelLimits": {
"description": "Per-model limits for a multimodal understanding model.",
"properties": {
"max_media_parts": {
"description": "Maximum media inputs per request.",
"title": "Max Media Parts",
"type": "integer"
},
"modalities": {
"description": "Input media modalities accepted by the named tool for this model.",
"items": {
"enum": [
"image",
"video",
"audio"
],
"type": "string"
},
"title": "Modalities",
"type": "array"
},
"reasoning_efforts": {
"description": "Accepted reasoning_effort values.",
"items": {
"type": "string"
},
"title": "Reasoning Efforts",
"type": "array"
},
"response_formats": {
"description": "Accepted response_format types.",
"items": {
"type": "string"
},
"title": "Response Formats",
"type": "array"
},
"supports_thinking": {
"description": "Whether deep thinking is available.",
"title": "Supports Thinking",
"type": "boolean"
}
},
"required": [
"modalities",
"max_media_parts",
"supports_thinking",
"reasoning_efforts",
"response_formats"
],
"title": "UnderstandingModelLimits",
"type": "object"
},
"VideoModelLimits": {
"description": "Per-model limits for a Seedance video model.",
"properties": {
"draft_final_resolution": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Resolution a Draft task renders to when finalized; null without Draft support.",
"title": "Draft Final Resolution"
},
"duration_seconds": {
"description": "Inclusive duration range in seconds; -1 (auto) is always accepted as well.",
"maxItems": 2,
"minItems": 2,
"prefixItems": [
{
"type": "integer"
},
{
"type": "integer"
}
],
"title": "Duration Seconds",
"type": "array"
},
"max_reference_audios": {
"description": "Maximum reference audio clips per request.",
"title": "Max Reference Audios",
"type": "integer"
},
"max_reference_images": {
"description": "Maximum reference images per request.",
"title": "Max Reference Images",
"type": "integer"
},
"max_reference_videos": {
"description": "Maximum reference videos per request.",
"title": "Max Reference Videos",
"type": "integer"
},
"output_formats": {
"description": "Accepted output_format values; empty when the field is unsupported.",
"items": {
"type": "string"
},
"title": "Output Formats",
"type": "array"
},
"ratios": {
"description": "Accepted ratio values.",
"items": {
"type": "string"
},
"title": "Ratios",
"type": "array"
},
"resolutions": {
"description": "Accepted resolution values.",
"items": {
"type": "string"
},
"title": "Resolutions",
"type": "array"
},
"supports_audio_only_input": {
"description": "Whether audio may be the only media input.",
"title": "Supports Audio Only Input",
"type": "boolean"
},
"supports_draft": {
"description": "Whether draft=true and draft_task_id are accepted.",
"title": "Supports Draft",
"type": "boolean"
},
"task_types": {
"description": "Accepted omni_reference_task_type values; empty when the field is unsupported.",
"items": {
"type": "string"
},
"title": "Task Types",
"type": "array"
}
},
"required": [
"resolutions",
"duration_seconds",
"ratios",
"max_reference_images",
"max_reference_videos",
"max_reference_audios",
"supports_draft",
"supports_audio_only_input",
"task_types",
"output_formats"
],
"title": "VideoModelLimits",
"type": "object"
}
},
"description": "Output model for ``ark_list_models``.",
"properties": {
"models": {
"description": "Configured models matching the filter.",
"items": {
"$ref": "#/$defs/ModelInfo"
},
"title": "Models",
"type": "array"
},
"pricing_note": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"description": "Why cached prices are unavailable, without credential values.",
"title": "Pricing Note"
},
"pricing_status": {
"default": "unavailable",
"description": "live if a fresh catalog snapshot exists; otherwise unavailable.",
"enum": [
"live",
"unavailable"
],
"title": "Pricing Status",
"type": "string"
},
"services": {
"description": "Enablement of each optional service.",
"items": {
"$ref": "#/$defs/ServiceStatus"
},
"title": "Services",
"type": "array"
}
},
"required": [
"models",
"services"
],
"title": "ArkListModelsOutput",
"type": "object"
}
  • Missing tool: check provider credentials and feature flags, then restart the connection.
  • Invalid arguments: keep the correct wrapper and follow current model limits from discovery. A valid schema alone does not prove the chosen model supports the combination.
  • A job completes with an error: inspect the original tool result, not only the outer job status. Never automatically resubmit potentially billable work.
  • Local output writes from jobs require server-configured OUTPUT_ROOTS; HTTP cannot write to a client’s local disk.

See configuration, background execution, and artifact delivery.