> ## 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.

# SDK integration

> Use OpenAI, Anthropic, Gemini, LangChain, or plain HTTP clients with Moxus AI endpoints.

Moxus AI supports common SDK workflows through compatible endpoints. Most applications can keep their current SDK and only change the API key and Base URL.

<Columns cols={3}>
  <Card title="OpenAI SDK" icon="code">
    Best default for chat, vision, tools, structured output, embeddings, and streaming.
  </Card>

  <Card title="Anthropic SDK" icon="braces">
    Use it when your app expects Claude-native Messages behavior.
  </Card>

  <Card title="LangChain" icon="blocks">
    Useful for retrieval, agents, and multi-tool orchestration.
  </Card>
</Columns>

<CodeGroup>
  ```python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-your-key",
      base_url="https://moxus.ai/v1",
  )

  response = client.chat.completions.create(
      model="gpt-4o",
      messages=[{"role": "user", "content": "Hello"}],
  )

  print(response.choices[0].message.content)
  ```

  ```javascript theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    apiKey: "sk-your-key",
    baseURL: "https://moxus.ai/v1",
  });

  const response = await client.chat.completions.create({
    model: "gpt-4o",
    messages: [{ role: "user", content: "Hello" }],
  });

  console.log(response.choices[0].message.content);
  ```
</CodeGroup>

## Next steps

* [Authentication](/en/guide/authentication)
* [Quickstart](/en/overview/quickstart)
* [Streaming](/en/guide/streaming)