> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/bytedance/deer-flow/llms.txt
> Use this file to discover all available pages before exploring further.

# Models API

> Query and retrieve available AI models and their configurations

## Overview

The Models API provides endpoints to query available AI models configured in DeerFlow. Models are configured in the application's configuration file and include metadata about their capabilities.

## List All Models

<Card title="GET /api/models" icon="list">
  Retrieve a list of all available AI models configured in the system
</Card>

### Response

<ResponseField name="models" type="array">
  List of all configured models with their metadata

  <Expandable title="Model Object">
    <ResponseField name="name" type="string" required>
      Unique identifier for the model
    </ResponseField>

    <ResponseField name="display_name" type="string">
      Human-readable name for display purposes
    </ResponseField>

    <ResponseField name="description" type="string">
      Description of the model's capabilities
    </ResponseField>

    <ResponseField name="supports_thinking" type="boolean" default="false">
      Whether the model supports thinking/reasoning mode
    </ResponseField>

    <ResponseField name="supports_reasoning_effort" type="boolean" default="false">
      Whether the model supports configurable reasoning effort levels
    </ResponseField>
  </Expandable>
</ResponseField>

### Example Request

```bash theme={null}
curl http://localhost:8001/api/models
```

### Example Response

```json theme={null}
{
  "models": [
    {
      "name": "gpt-4",
      "display_name": "GPT-4",
      "description": "OpenAI GPT-4 model",
      "supports_thinking": false,
      "supports_reasoning_effort": false
    },
    {
      "name": "claude-3-opus",
      "display_name": "Claude 3 Opus",
      "description": "Anthropic Claude 3 Opus model",
      "supports_thinking": true,
      "supports_reasoning_effort": false
    },
    {
      "name": "o1",
      "display_name": "OpenAI o1",
      "description": "OpenAI o1 reasoning model",
      "supports_thinking": false,
      "supports_reasoning_effort": true
    }
  ]
}
```

***

## Get Model Details

<Card title="GET /api/models/{model_name}" icon="circle-info">
  Retrieve detailed information about a specific AI model by its name
</Card>

### Path Parameters

<ParamField path="model_name" type="string" required>
  The unique name of the model to retrieve (e.g., `gpt-4`, `claude-3-opus`)
</ParamField>

### Response

<ResponseField name="name" type="string" required>
  Unique identifier for the model
</ResponseField>

<ResponseField name="display_name" type="string">
  Human-readable name
</ResponseField>

<ResponseField name="description" type="string">
  Model description
</ResponseField>

<ResponseField name="supports_thinking" type="boolean" default="false">
  Whether model supports thinking mode
</ResponseField>

<ResponseField name="supports_reasoning_effort" type="boolean" default="false">
  Whether model supports reasoning effort
</ResponseField>

### Example Request

```bash theme={null}
curl http://localhost:8001/api/models/gpt-4
```

### Example Response

```json theme={null}
{
  "name": "gpt-4",
  "display_name": "GPT-4",
  "description": "OpenAI GPT-4 model",
  "supports_thinking": false,
  "supports_reasoning_effort": false
}
```

### Error Responses

<ResponseField name="404" type="Not Found">
  Model not found

  ```json theme={null}
  {
    "detail": "Model 'invalid-model' not found"
  }
  ```
</ResponseField>

***

## Model Capabilities

### Thinking Mode

Models with `supports_thinking: true` can use extended thinking/reasoning capabilities. This is typically available in Claude models.

### Reasoning Effort

Models with `supports_reasoning_effort: true` support configurable reasoning effort levels (e.g., OpenAI's o1 series). This allows you to control how much computational effort the model applies to reasoning.

## Use Cases

### Frontend Model Selection

Use the `/api/models` endpoint to populate model selection dropdowns:

```typescript theme={null}
const response = await fetch('http://localhost:8001/api/models');
const { models } = await response.json();

// Filter models with specific capabilities
const thinkingModels = models.filter(m => m.supports_thinking);
const reasoningModels = models.filter(m => m.supports_reasoning_effort);
```

### Capability Detection

Check if a specific model supports certain features:

```typescript theme={null}
const response = await fetch(`http://localhost:8001/api/models/${modelName}`);
const model = await response.json();

if (model.supports_thinking) {
  // Show thinking mode toggle
}
```

## Related

<CardGroup cols={2}>
  <Card title="Gateway Overview" icon="book" href="/api/gateway/overview">
    Learn about the Gateway API
  </Card>

  <Card title="Configuration" icon="gear" href="/customize/configuration">
    Configure AI models
  </Card>
</CardGroup>