> ## 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

> Use Claude, OpenAI, and Gemini compatible APIs through APIXO

APIXO is a drop-in LLM API gateway. If your code or app already supports Claude, OpenAI, or Gemini API formats, you usually only need to change the base URL, API key, and model id.

## Fastest setup

1. Create an API key in the [APIXO dashboard](https://apixo.ai/dashboard/api-keys).
2. Store it as `APIXO_API_KEY`.
3. Use the compatible API format your app already supports.
4. Change the `model` value when you want to switch models.

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

## Choose your API format

| If your app supports | Use this Base URL         | API key setting | Model example            |
| -------------------- | ------------------------- | --------------- | ------------------------ |
| Claude / Anthropic   | `https://llm.apixo.ai`    | `APIXO_API_KEY` | `claude-sonnet-4-6`      |
| OpenAI Responses     | `https://llm.apixo.ai/v1` | `APIXO_API_KEY` | `gpt-5.4`                |
| Gemini               | `https://llm.apixo.ai`    | `APIXO_API_KEY` | `gemini-3.1-pro-preview` |

<Tip>
  APIXO keeps the official request and response formats. Do not rewrite your payload unless you are also changing provider format.
</Tip>

## Minimal requests

<Tabs>
  <Tab title="Claude">
    ```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-sonnet-4-6",
        "max_tokens": 256,
        "messages": [
          {"role": "user", "content": "Say hello in one sentence."}
        ]
      }'
    ```
  </Tab>

  <Tab title="OpenAI">
    ```bash theme={null}
    curl -X POST "https://llm.apixo.ai/v1/responses" \
      -H "Authorization: Bearer $APIXO_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "gpt-5.4",
        "input": "Say hello in one sentence."
      }'
    ```
  </Tab>

  <Tab title="Gemini">
    ```bash theme={null}
    curl -X POST "https://llm.apixo.ai/v1beta/models/gemini-3.1-pro-preview:generateContent" \
      -H "x-goog-api-key: $APIXO_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "contents": [
          {
            "role": "user",
            "parts": [{"text": "Say hello in one sentence."}]
          }
        ]
      }'
    ```
  </Tab>
</Tabs>

## Switch models

To switch models, keep the same API format and change only the model id.

| API format       | Where to change the model                         |
| ---------------- | ------------------------------------------------- |
| Claude           | Request body `model`                              |
| OpenAI Responses | Request body `model`                              |
| Gemini           | URL path `/v1beta/models/{model}:generateContent` |

See [Supported Models](/docs/llm/supported-models) for the current model ids.

## Next steps

<CardGroup>
  <Card title="Use official SDKs" href="/docs/llm/official-sdks">
    Configure Claude, OpenAI, and Gemini compatible SDK clients.
  </Card>

  <Card title="Configure third-party apps" href="/docs/llm/third-party-apps">
    Use APIXO in apps that accept a custom provider endpoint.
  </Card>

  <Card title="Supported models" href="/docs/llm/supported-models">
    Copy a model id for Claude, OpenAI, or Gemini compatible requests.
  </Card>

  <Card title="Errors and retry" href="/docs/llm/errors-retry">
    Troubleshoot authentication, unsupported models, and upstream failures.
  </Card>
</CardGroup>