> ## Documentation Index
> Fetch the complete documentation index at: https://docs.bland.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Get Model Profile Catalog

> List the model profiles available to extractors.

### Overview

<Note>
  Dispositions are enabled per organization. If your organization does not have access, these endpoints return `404`.
</Note>

Returns the model profiles an extractor's `inferenceConfig.modelProfileKey` may name. A profile is an opaque handle for a quality, latency, and cost trade-off; only profiles currently available for structured extraction are listed. Use a profile's `key` in [Create Disposition Extractor](/api-v2/post/agents-id-dispositions-extractors) or [Update Disposition Extractor Draft](/api-v2/patch/agents-id-dispositions-extractors-extractor-id-draft).

### Headers

<ParamField header="authorization" type="string" required>
  Your API key for authentication.
</ParamField>

### Path Parameters

<ParamField path="agent_id" type="string" required>
  The agent's unique identifier. A malformed id returns `400` with the message `agentId must be a valid UUID`.
</ParamField>

### Response

<ResponseField name="data.profiles" type="array">
  Array of model profile entries.

  <Expandable title="profile entry">
    <ResponseField name="key" type="string">
      The value to pass as `modelProfileKey`. `balanced` is the default when an extractor omits the key.
    </ResponseField>

    <ResponseField name="label" type="string">
      Human-readable name for the profile.
    </ResponseField>

    <ResponseField name="description" type="string">
      One sentence on when to choose this profile.
    </ResponseField>

    <ResponseField name="supportsAudio" type="boolean">
      `true` when an extractor using this profile may include `audio_recording` in `contextSources`. Profiles with `false` reject that source with a `400`.
    </ResponseField>

    <ResponseField name="supportsBatch" type="boolean">
      Reserved. Currently always `false`.
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="errors" type="null | array">
  `null` on success, or a list of error objects if the request failed.
</ResponseField>

<ResponseExample>
  ```json Response theme={null}
  {
    "data": {
      "profiles": [
        {
          "key": "balanced",
          "label": "Balanced",
          "description": "Recommended quality, latency, and cost for most calls.",
          "supportsAudio": true,
          "supportsBatch": false
        },
        {
          "key": "fast",
          "label": "Fast",
          "description": "Lower latency for straightforward text extraction.",
          "supportsAudio": false,
          "supportsBatch": false
        },
        {
          "key": "high_accuracy",
          "label": "High accuracy",
          "description": "More reasoning for complex text extraction.",
          "supportsAudio": false,
          "supportsBatch": false
        }
      ]
    },
    "errors": null
  }
  ```

  ```json Not Found theme={null}
  {
    "data": null,
    "errors": [
      {
        "error": "NOT_FOUND",
        "message": "Agent not found"
      }
    ]
  }
  ```
</ResponseExample>

***

Docs for agents: [llms.txt](/llms.txt)