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

# Integrate Meliai into Your Existing AI Tools Stack

> Meliai works with any tool that speaks OpenAI or Anthropic. Connect LangChain, Vercel AI SDK, n8n, and more with a single configuration change.

Meliai is designed for drop-in compatibility — if your tool, framework, or workflow already talks to OpenAI or Anthropic, you can point it at Meliai with a single configuration change. Swap the base URL to `https://api.meliai.ai/v1`, set your `sk-mel-<KEY>` API key, and everything from chains and agents to streaming route handlers keeps working exactly as before, now routed across sovereign European infrastructure.

<CardGroup cols={2}>
  <Card title="LangChain" icon="link" href="/integrations/langchain">
    Use `ChatOpenAI` with a custom `base_url` to connect LangChain chains, agents, and memory to Meliai.
  </Card>

  <Card title="Vercel AI SDK" icon="triangle" href="/integrations/vercel-ai-sdk">
    Use the `@ai-sdk/openai` provider with a custom `baseURL` in Next.js route handlers and server actions.
  </Card>

  <Card title="n8n" icon="workflow" href="/integrations/n8n">
    Configure the OpenAI Chat Model node in n8n with your Meliai API key and base URL to run AI workflows.
  </Card>

  <Card title="OpenAI SDK" icon="code" href="/get-started/from-openai">
    Already using the OpenAI Python or Node.js SDK? Set `base_url` to Meliai and you're done.
  </Card>

  <Card title="Anthropic SDK" icon="robot" href="/get-started/from-anthropic">
    The Anthropic Python and Node.js SDKs work with Meliai's `/v1/messages` endpoint out of the box.
  </Card>
</CardGroup>

## Any OpenAI-compatible client

Meliai follows the OpenAI API shape, so any client library, proxy, or tool that lets you configure a base URL will work. The general pattern is:

1. Set the **base URL** to `https://api.meliai.ai/v1`
2. Set the **API key** to your `sk-mel-<KEY>` value

That's all. Model names, request bodies, streaming, and response formats stay identical to what you already use.

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

  client = openai.OpenAI(
      api_key="sk-mel-...",
      base_url="https://api.meliai.ai/v1",
  )
  ```

  ```typescript Node.js theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    apiKey: process.env.MELIAI_API_KEY,
    baseURL: "https://api.meliai.ai/v1",
  });
  ```

  ```bash curl theme={null}
  curl https://api.meliai.ai/v1/chat/completions \
    -H "Authorization: Bearer sk-mel-..." \
    -H "Content-Type: application/json" \
    -d '{"model": "<MODEL_ID>", "messages": [{"role": "user", "content": "Hello"}]}'
  ```
</CodeGroup>

<Note>
  Meliai also supports the Anthropic Messages API shape at `/v1/messages`. Point any Anthropic-compatible client at `https://api.meliai.ai` and use your `sk-mel-<KEY>` as the API key.
</Note>