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

# FAQ

> Answers to common questions about using Anyone.

<AccordionGroup>
  <Accordion title="What's the difference between Anyone and using OpenAI/Claude directly?">
    Anyone aggregates 40+ AI providers. You only need one API key to call all models — no need to register separately with OpenAI, Anthropic, Google, etc. Plus, Anyone automatically handles format conversion, so you can use the OpenAI SDK to call Claude and Gemini.
  </Accordion>

  <Accordion title="Does it support the OpenAI Python/JavaScript SDK?">
    Fully supported. Just set `base_url` and `api_key`:

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

    client = OpenAI(
        base_url="https://api.anyone.ai/v1",
        api_key="YOUR_TOKEN",
    )
    ```

    All features supported by the OpenAI SDK (chat completions, streaming, function calling, etc.) work out of the box.
  </Accordion>

  <Accordion title="Can I call Claude using the OpenAI format?">
    Yes. Send a standard `/v1/chat/completions` request with the model set to a Claude model name like `claude-sonnet-4-6`. Anyone automatically converts the request to Claude Messages format and converts the response back to OpenAI format.

    The reverse also works — Anyone's `/v1/messages` endpoint supports the native Claude format.
  </Accordion>

  <Accordion title="Does it support streaming?">
    Yes. Set `"stream": true` in your request:

    ```json theme={null}
    {
      "model": "gpt-5.4",
      "stream": true,
      "messages": [{"role": "user", "content": "Hello"}]
    }
    ```

    Responses are returned in real time using SSE (Server-Sent Events) format.
  </Accordion>

  <Accordion title="Does it support function calling / tool use?">
    Yes. Pass the `tools` parameter in your request, exactly as you would with OpenAI. Anyone automatically converts tool calling to the format supported by the target model.
  </Accordion>

  <Accordion title="What if I forget my password?">
    Click **Forgot password** on the login page and follow the instructions to reset it.
  </Accordion>

  <Accordion title="What if my API key is leaked?">
    Immediately log in to the dashboard and delete the API key, then create a new one. A deleted API key is invalidated instantly.
  </Accordion>

  <Accordion title="What models are available?">
    Call the `/v1/models` endpoint for the full list:

    ```bash theme={null}
    curl https://api.anyone.ai/v1/models \
      -H "Authorization: Bearer YOUR_TOKEN"
    ```

    You can also check the models page in the dashboard.
  </Accordion>

  <Accordion title="Which client tools are supported?">
    Any tool compatible with the OpenAI API works, including:

    * **Cherry Studio** — set the base URL to `https://api.anyone.ai/v1`
    * **LangChain** / **LlamaIndex** — change the base URL in the configuration
    * **Vercel AI SDK** — use the OpenAI provider and change the base URL
    * **Cursor / Continue** — set a custom API endpoint
    * And any other tool that supports a custom OpenAI endpoint
  </Accordion>

  <Accordion title="How do I debug a failed request?">
    See the [troubleshooting](/support/troubleshooting) page for common error codes and solutions.
  </Accordion>
</AccordionGroup>