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

# Authentication

> Use API keys to authenticate requests to OpenAI, Anthropic, and Gemini compatible endpoints.

Moxus AI authenticates requests with API keys. Every programmatic request must include a valid key so the platform can verify identity, permissions, quota, and model access.

<Columns cols={3}>
  <Card title="OpenAI compatible" icon="message-square-code">
    `https://moxus.ai/v1`
  </Card>

  <Card title="Anthropic compatible" icon="braces">
    `https://moxus.ai`
  </Card>

  <Card title="Gemini compatible" icon="sparkles">
    `https://moxus.ai/v1beta`
  </Card>
</Columns>

## Authorization header

Most OpenAI-compatible requests use a Bearer token.

```text theme={null}
Authorization: Bearer sk-your-key
```

```bash theme={null}
curl https://moxus.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello"}]}'
```

<Warning>
  Never expose API keys in browser frontend code, public repositories, screenshots, or shared chat messages.
</Warning>

## Recommended setup

* Use environment variables for keys and base URLs.
* Create separate keys for development, production, and third-party clients.
* Set quota and expiration limits for temporary or external use cases.
* Rotate keys if you suspect exposure.

## Next steps

* [Account and API keys](/en/platform/account-and-keys)
* [SDK integration](/en/integrations/sdks)