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

# Chat completions

> Create chat completions using the OpenAI-compatible endpoint

Create a chat completion using the `/chat/completions` endpoint. This endpoint follows the OpenAI format for sending messages and receiving responses.

## Requirements

To create a chat completion, provide:

* The Inference service base URL: `https://api.inference.wandb.ai/v1`.
* Your W\&B API key: `[YOUR-API-KEY]`.
* Your W\&B team and project: `[YOUR-TEAM]/[YOUR-PROJECT]` (optional).
* A model ID from the [available models](/inference/models).

## Request examples

The following examples show how to send a chat completion request using Python and `curl`. Replace the placeholder values with your own API key, optional team and project, and a model ID.

<Tabs>
  <Tab title="Python">
    ```python theme={null}
    import openai

    client = openai.OpenAI(
        # The custom base URL points to Serverless Inference
        base_url='https://api.inference.wandb.ai/v1',

        # Create an API key at https://wandb.ai/settings
        # Consider setting it in the environment as OPENAI_API_KEY instead for safety
        api_key="[YOUR-API-KEY]",

        # Optional: Team and project for usage tracking
        project="[YOUR-TEAM]/[YOUR-PROJECT]",
    )

    # Replace [MODEL-ID] with any model ID from the available models list
    response = client.chat.completions.create(
        model="[MODEL-ID]",
        messages=[
            {"role": "system", "content": "[YOUR-SYSTEM-PROMPT]"},
            {"role": "user", "content": "[YOUR-PROMPT]"}
        ],
    )

    print(response.choices[0].message.content)
    ```
  </Tab>

  <Tab title="Bash">
    ```bash theme={null}
    curl https://api.inference.wandb.ai/v1/chat/completions \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer [YOUR-API-KEY]" \
      -H "OpenAI-Project: [YOUR-TEAM]/[YOUR-PROJECT]" \
      -d '{
        "model": "[MODEL-ID]",
        "messages": [
          { "role": "system", "content": "You are a helpful assistant." },
          { "role": "user", "content": "Tell me a joke." }
        ]
      }'
    ```
  </Tab>
</Tabs>

## Response format

A successful request returns a response in the following OpenAI-compatible format, including the generated assistant message and token usage details.

```json theme={null}
{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "meta-llama/Llama-3.1-8B-Instruct",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here's a joke for you..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 50,
    "total_tokens": 75
  }
}
```