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

# Authentication

> Find your GGUF Cloud deployment's base URL and authenticate with your existing ModelsLab API key using the Authorization, x-api-key, or key header.

Every GGUF Cloud deployment is a private endpoint with its own base URL, authenticated with your existing ModelsLab API key. No separate key is required.

## Base URL

Each deployment has a unique base URL. The `{deployment_id}` is shown on the deployment's dashboard page at [modelslab.com/gguf-cloud](https://modelslab.com/gguf-cloud):

```
https://modelslab.com/api/gguf/{deployment_id}
```

### Choosing the right base\_url

The two SDK families expect the base URL in slightly different forms. Use the matching one:

| SDK / Client                            | `base_url` value                                    |
| --------------------------------------- | --------------------------------------------------- |
| OpenAI SDK (Python, Node, LangChain, …) | `https://modelslab.com/api/gguf/{deployment_id}/v1` |
| Anthropic SDK / Claude Code             | `https://modelslab.com/api/gguf/{deployment_id}`    |

<Note>
  The OpenAI SDK appends paths like `/chat/completions` to the base URL, so the base URL ends in `/v1`. The Anthropic SDK appends `/v1/messages` itself, so its base URL is the **root** (no trailing `/v1`).
</Note>

## API key

Authenticate with your existing **ModelsLab API key**. You can find or create one in your [API Keys Dashboard](https://modelslab.com/dashboard/api-keys). The gateway accepts the key in any of three headers, so SDKs from both ecosystems work unchanged:

<ParamField header="Authorization" type="string">
  Bearer token form used by OpenAI SDKs: `Authorization: Bearer YOUR_MODELSLAB_API_KEY`
</ParamField>

<ParamField header="x-api-key" type="string">
  Header used by Anthropic SDKs and Claude Code: `x-api-key: YOUR_MODELSLAB_API_KEY`
</ParamField>

<ParamField header="key" type="string">
  Plain header form: `key: YOUR_MODELSLAB_API_KEY`
</ParamField>

<Warning>
  Never share your API key publicly or commit it to version control. Treat it like a password and use environment variables in production.
</Warning>

## Examples

<CodeGroup>
  ```python Python (OpenAI SDK) theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_MODELSLAB_API_KEY",
      base_url="https://modelslab.com/api/gguf/YOUR_DEPLOYMENT_ID/v1",
  )
  ```

  ```python Python (Anthropic SDK) theme={null}
  from anthropic import Anthropic

  client = Anthropic(
      api_key="YOUR_MODELSLAB_API_KEY",
      base_url="https://modelslab.com/api/gguf/YOUR_DEPLOYMENT_ID",
  )
  ```

  ```bash cURL (Authorization) theme={null}
  curl "https://modelslab.com/api/gguf/YOUR_DEPLOYMENT_ID/v1/models" \
    -H "Authorization: Bearer $MODELSLAB_API_KEY"
  ```

  ```bash cURL (x-api-key) theme={null}
  curl "https://modelslab.com/api/gguf/YOUR_DEPLOYMENT_ID/v1/models" \
    -H "x-api-key: $MODELSLAB_API_KEY"
  ```
</CodeGroup>

## Next steps

<CardGroup cols={2}>
  <Card title="Chat Completions" href="/gguf-cloud/chat-completions" icon="comments">
    Call the OpenAI-compatible endpoints on your deployment.
  </Card>

  <Card title="Messages" href="/gguf-cloud/messages" icon="message">
    Call the Anthropic-compatible endpoint, or point Claude Code at your deployment.
  </Card>
</CardGroup>