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

# Using the SDKs

> Point the OpenAI and Anthropic client libraries at Relay

Relay speaks the OpenAI and Anthropic wire protocols, so you don't need a new
client library — point the official SDK you already use at Relay's base URL
and pass your **relay key** as the API key. Relay accepts the key whether the
SDK sends it as a bearer token or an `x-api-key` header, so this just works.

| SDK       | Base URL                          | Endpoint it calls             |
| --------- | --------------------------------- | ----------------------------- |
| OpenAI    | `http://localhost:8080/openai/v1` | `/openai/v1/chat/completions` |
| Anthropic | `http://localhost:8080/anthropic` | `/anthropic/v1/messages`      |

<Info>
  Swap `http://localhost:8080` for your relay's public URL in production. The
  data plane is the inference port (`8080` by default).
</Info>

## OpenAI shape

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

  client = OpenAI(
      base_url="http://localhost:8080/openai/v1",
      api_key="<your-relay-key>",
  )

  resp = client.chat.completions.create(
      model="gpt-4o",
      messages=[{"role": "user", "content": "hello"}],
  )
  print(resp.choices[0].message.content)
  ```

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

  const client = new OpenAI({
    baseURL: "http://localhost:8080/openai/v1",
    apiKey: "<your-relay-key>",
  });

  const resp = await client.chat.completions.create({
    model: "gpt-4o",
    messages: [{ role: "user", content: "hello" }],
  });
  console.log(resp.choices[0].message.content);
  ```

  ```bash cURL theme={null}
  curl http://localhost:8080/openai/v1/chat/completions \
    -H "Authorization: Bearer <your-relay-key>" \
    -H "Content-Type: application/json" \
    -d '{"model":"gpt-4o","messages":[{"role":"user","content":"hello"}]}'
  ```
</CodeGroup>

## Anthropic shape

<CodeGroup>
  ```python Python theme={null}
  from anthropic import Anthropic

  client = Anthropic(
      base_url="http://localhost:8080/anthropic",
      api_key="<your-relay-key>",
  )

  msg = client.messages.create(
      model="claude-sonnet-4-6",
      max_tokens=256,
      messages=[{"role": "user", "content": "hello"}],
  )
  print(msg.content[0].text)
  ```

  ```javascript Node theme={null}
  import Anthropic from "@anthropic-ai/sdk";

  const client = new Anthropic({
    baseURL: "http://localhost:8080/anthropic",
    apiKey: "<your-relay-key>",
  });

  const msg = await client.messages.create({
    model: "claude-sonnet-4-6",
    max_tokens: 256,
    messages: [{ role: "user", content: "hello" }],
  });
  console.log(msg.content[0].text);
  ```

  ```bash cURL theme={null}
  curl http://localhost:8080/anthropic/v1/messages \
    -H "Authorization: Bearer <your-relay-key>" \
    -H "Content-Type: application/json" \
    -d '{"model":"claude-sonnet-4-6","max_tokens":256,"messages":[{"role":"user","content":"hello"}]}'
  ```
</CodeGroup>

## Streaming

Both SDKs stream as usual — Relay passes the event stream straight through.

<CodeGroup>
  ```python OpenAI · Python theme={null}
  stream = client.chat.completions.create(
      model="gpt-4o",
      messages=[{"role": "user", "content": "hello"}],
      stream=True,
  )
  for chunk in stream:
      print(chunk.choices[0].delta.content or "", end="")
  ```

  ```python Anthropic · Python theme={null}
  with client.messages.stream(
      model="claude-sonnet-4-6",
      max_tokens=256,
      messages=[{"role": "user", "content": "hello"}],
  ) as stream:
      for text in stream.text_stream:
          print(text, end="")
  ```
</CodeGroup>

## Which models can I call?

The `model` you pass must be granted by your relay key's policy and have an
enabled host binding. List what your key can reach:

```bash theme={null}
curl http://localhost:8080/v1/models \
  -H "Authorization: Bearer <your-relay-key>"
```

See [Troubleshooting](/troubleshooting) if a model returns `403` or `404`.