Models

LLM gateway and per-task configuration.

10 actions. Each is callable by the agent as a tool, over HTTP via /api/invoke, and (usually) from a UI page.

`models.list`

GET

List models available via the gateway. Filter by provider (anthropic, openai, google, …) or a free-text search. Pass limit (+ optional offset) for a single server-side page — the response then includes total and hasMore; omit limit to get the whole catalog.

AI tool: models_list
API: GET /api/invoke/models.list

Input

Field	Type	Required
`provider`	string	—
`search`	string	—
`limit`	integer	—
`offset`	integer	—

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "provider": {
      "type": "string"
    },
    "search": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "exclusiveMinimum": 0,
      "maximum": 1000
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  }
}

`models.get_default`

GET

Get the current default chat model id.

AI tool: models_get_default
API: GET /api/invoke/models.get_default

Input

No parameters.

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {},
  "additionalProperties": {}
}

`models.set_default`

POST · mutating

Set the default chat model id.

AI tool: models_set_default
API: POST /api/invoke/models.set_default

Input

Field	Type	Required	Description
`modelId`	string	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "modelId": {
      "type": "string"
    }
  },
  "required": [
    "modelId"
  ]
}

`models.list_preferred`

GET

List the curated shortlist of preferred model ids (for the in-chat model picker).

AI tool: models_list_preferred
API: GET /api/invoke/models.list_preferred

Input

No parameters.

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {},
  "additionalProperties": {}
}

`models.set_preferred`

POST · mutating

Replace the preferred-models shortlist with the given ordered ids.

AI tool: models_set_preferred
API: POST /api/invoke/models.set_preferred

Input

Field	Type	Required	Description
`modelIds`	string[]	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "modelIds": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "required": [
    "modelIds"
  ]
}

`models.toggle_preferred`

POST · mutating

Add or remove a model from the preferred shortlist. If the model is already preferred it gets removed; otherwise appended.

AI tool: models_toggle_preferred
API: POST /api/invoke/models.toggle_preferred

Input

Field	Type	Required	Description
`modelId`	string	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "modelId": {
      "type": "string"
    }
  },
  "required": [
    "modelId"
  ]
}

`models.get_config`

GET

Get full per-task model configuration (chat-agent, embeddings, image-gen, etc.).

AI tool: models_get_config
API: GET /api/invoke/models.get_config

Input

No parameters.

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {},
  "additionalProperties": {}
}

`models.set_task_model`

POST · mutating

Set the model id for a given task (chat-agent, embeddings, image-gen, etc.).

AI tool: models_set_task_model
API: POST /api/invoke/models.set_task_model

Input

Field	Type	Required	Description
`task`	"chat-agent" \| "embeddings" \| "image-gen" \| "video-gen" \| "tts" \| "music" \| "fast-routing" \| "vision" \| "voice-derive" \| "draft-generate"	yes
`modelId`	string	yes

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "enum": [
        "chat-agent",
        "embeddings",
        "image-gen",
        "video-gen",
        "tts",
        "music",
        "fast-routing",
        "vision",
        "voice-derive",
        "draft-generate"
      ]
    },
    "modelId": {
      "type": "string"
    }
  },
  "required": [
    "task",
    "modelId"
  ]
}

`models.set_task_settings`

PATCH · mutating

Update tuning parameters (temperature, maxTokens, topP, fallback, extras) for a task.

AI tool: models_set_task_settings
API: PATCH /api/invoke/models.set_task_settings

Input

Field	Type	Required
`task`	"chat-agent" \| "embeddings" \| "image-gen" \| "video-gen" \| "tts" \| "music" \| "fast-routing" \| "vision" \| "voice-derive" \| "draft-generate"	yes
`temperature`	number	—
`maxTokens`	integer	—
`topP`	number	—
`fallback`	string[]	—
`extras`	object	—

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "task": {
      "type": "string",
      "enum": [
        "chat-agent",
        "embeddings",
        "image-gen",
        "video-gen",
        "tts",
        "music",
        "fast-routing",
        "vision",
        "voice-derive",
        "draft-generate"
      ]
    },
    "temperature": {
      "type": "number",
      "minimum": 0,
      "maximum": 2
    },
    "maxTokens": {
      "type": "integer",
      "minimum": 1,
      "maximum": 9007199254740991
    },
    "topP": {
      "type": "number",
      "minimum": 0,
      "maximum": 1
    },
    "fallback": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "extras": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    }
  },
  "required": [
    "task"
  ]
}

`models.recent_traces`

GET

Recent LLM call traces for observability — model id, tokens, latency, status.

AI tool: models_recent_traces
API: GET /api/invoke/models.recent_traces

Input

Field	Type	Required
`limit`	integer	—
`offset`	integer	—
`orderBy`	string	—
`orderDir`	"asc" \| "desc"	—
`q`	string	—

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 500
    },
    "offset": {
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    },
    "orderBy": {
      "type": "string"
    },
    "orderDir": {
      "type": "string",
      "enum": [
        "asc",
        "desc"
      ]
    },
    "q": {
      "type": "string"
    }
  }
}