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

# GET /v1/models

> List all available models on Inferoute. Returns model IDs, provider, context window, and capabilities. Use model IDs in your chat and completion requests.

The models endpoint returns every model currently available on Inferoute, along with metadata about each one. Use the `id` field from this response when specifying the `model` parameter in your chat, completion, and embedding requests.

## Endpoint

```
GET https://api.inferoute.ai/v1/models
```

No request body is required. Include your `Authorization` header as with all Inferoute requests.

## Response fields

<ResponseField name="object" type="string">
  Always `"list"`.
</ResponseField>

<ResponseField name="data" type="object[]">
  Array of model objects, one per available model.

  <Expandable title="properties">
    <ResponseField name="id" type="string">
      The model identifier to use in API requests. Typically in `provider/model-name` format, e.g. `openai/gpt-4o` or `anthropic/claude-3-5-sonnet`.
    </ResponseField>

    <ResponseField name="object" type="string">
      Always `"model"`.
    </ResponseField>

    <ResponseField name="owned_by" type="string">
      The provider that owns this model, e.g. `openai`, `anthropic`, `google`, `meta`.
    </ResponseField>

    <ResponseField name="context_window" type="integer">
      Maximum number of tokens the model can process in a single request (prompt + completion combined).
    </ResponseField>

    <ResponseField name="capabilities" type="object">
      <Expandable title="properties">
        <ResponseField name="chat" type="boolean">
          Whether this model can be used with the `/v1/chat/completions` endpoint.
        </ResponseField>

        <ResponseField name="completions" type="boolean">
          Whether this model can be used with the `/v1/completions` endpoint.
        </ResponseField>

        <ResponseField name="embeddings" type="boolean">
          Whether this model can be used with the `/v1/embeddings` endpoint.
        </ResponseField>
      </Expandable>
    </ResponseField>
  </Expandable>
</ResponseField>

## Example

<CodeGroup>
  ```bash curl theme={null}
  curl https://api.inferoute.ai/v1/models \
    --header "Authorization: Bearer YOUR_API_KEY"
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://api.inferoute.ai/v1",
  )

  models = client.models.list()
  for model in models.data:
      print(model.id)
  ```

  ```javascript Node.js theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    apiKey: "YOUR_API_KEY",
    baseURL: "https://api.inferoute.ai/v1",
  });

  const models = await client.models.list();
  for (const model of models.data) {
    console.log(model.id);
  }
  ```
</CodeGroup>

**Response:**

```json theme={null}
{
  "object": "list",
  "data": [
    {
      "id": "openai/gpt-4o",
      "object": "model",
      "owned_by": "openai",
      "context_window": 128000,
      "capabilities": {
        "chat": true,
        "completions": false,
        "embeddings": false
      }
    },
    {
      "id": "anthropic/claude-3-5-sonnet",
      "object": "model",
      "owned_by": "anthropic",
      "context_window": 200000,
      "capabilities": {
        "chat": true,
        "completions": false,
        "embeddings": false
      }
    },
    {
      "id": "openai/gpt-3.5-turbo-instruct",
      "object": "model",
      "owned_by": "openai",
      "context_window": 4096,
      "capabilities": {
        "chat": false,
        "completions": true,
        "embeddings": false
      }
    },
    {
      "id": "text-embedding-3-small",
      "object": "model",
      "owned_by": "openai",
      "context_window": 8191,
      "capabilities": {
        "chat": false,
        "completions": false,
        "embeddings": true
      }
    },
    {
      "id": "text-embedding-3-large",
      "object": "model",
      "owned_by": "openai",
      "context_window": 8191,
      "capabilities": {
        "chat": false,
        "completions": false,
        "embeddings": true
      }
    },
    {
      "id": "google/gemini-1.5-pro",
      "object": "model",
      "owned_by": "google",
      "context_window": 2097152,
      "capabilities": {
        "chat": true,
        "completions": false,
        "embeddings": false
      }
    }
  ]
}
```

<Tip>
  Filter the `data` array by `capabilities.embeddings === true` to get only models that work with the `/v1/embeddings` endpoint, or by `capabilities.chat === true` for chat-capable models. This avoids trial-and-error when selecting a model for a specific endpoint.
</Tip>