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

# LLM Gateway Authentication with Your APIXO API Key

> Use your APIXO API key with the Claude, OpenAI, and Gemini compatible endpoints on the APIXO LLM Gateway, and manage it in the dashboard.

LLM Gateway requests use your APIXO API key. The header name follows the compatible provider API so existing SDKs and tools can keep their normal request format.

Create a key in the [APIXO dashboard](https://apixo.ai/dashboard/api-keys), then store it as `APIXO_API_KEY`.

```bash theme={null}
export APIXO_API_KEY="your_apixo_api_key"
```

## Header by API format

| Compatible API | Header |
| - | - |
| Claude API | `x-api-key: $APIXO_API_KEY` |
| OpenAI Responses API | `Authorization: Bearer $APIXO_API_KEY` |
| Gemini API | `x-goog-api-key: $APIXO_API_KEY` |

## Claude required version header

Claude-compatible requests also require the Anthropic protocol version header. Most Claude SDKs add this automatically.

```http theme={null}
anthropic-version: 2023-06-01
```

## Example

```bash theme={null}
curl -X POST "https://llm.apixo.ai/v1/messages" \
  -H "x-api-key: $APIXO_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 128,
    "messages": [{"role": "user", "content": "Say hello."}]
  }'
```

<Tip>
  Do not expose APIXO keys in browser-side code. Make LLM Gateway calls from your backend, serverless function, or trusted runtime.
</Tip>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.