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

# Mistral AI

> Auto-trace Mistral AI chat completions

### Installation

<Tabs>
  <Tab title="pip">
    ```bash theme={null}
    pip install "pandaprobe[mistral]"
    ```
  </Tab>

  <Tab title="uv">
    ```bash theme={null}
    uv add "pandaprobe[mistral]"
    ```
  </Tab>
</Tabs>

### Setup

<Tabs>
  <Tab title="Sync">
    ```python theme={null}
    from pandaprobe.wrappers import wrap_mistral
    from mistralai.client import Mistral

    client = wrap_mistral(Mistral(api_key="..."))
    ```
  </Tab>

  <Tab title="Async">
    ```python theme={null}
    from pandaprobe.wrappers import wrap_mistral
    from mistralai.client import Mistral

    # The Mistral SDK exposes both sync and async on the same client.
    client = wrap_mistral(Mistral(api_key="..."))

    response = await client.chat.complete_async(
        model="mistral-small-latest",
        messages=[{"role": "user", "content": "Hello!"}],
    )
    ```
  </Tab>
</Tabs>

## Chat API

Span name: `"mistral-chat"`, SpanKind: `LLM`

```python theme={null}
response = client.chat.complete(
    model="mistral-small-latest",
    messages=[
        {"role": "system", "content": "You are a concise assistant."},
        {"role": "user", "content": "Explain recursion in one sentence."},
    ],
    temperature=0.5,
    max_tokens=200,
)
```

**What gets traced**

* Input: `messages` list, captured directly (Mistral already speaks the universal schema)
* Output: assistant message from `choices[0].message`
* Model name (from the response body)
* Token usage
* Model parameters: `temperature`, `top_p`, `max_tokens`, `random_seed`, `safe_prompt`, `response_format`, `tool_choice`, `presence_penalty`, `frequency_penalty`, `n`, `stop`

### Streaming

<CodeGroup>
  ```python title="chat.stream — sync" theme={null}
  res = client.chat.stream(
      model="mistral-small-latest",
      messages=[{"role": "user", "content": "Hello!"}],
  )
  with res as event_stream:
      for event in event_stream:
          delta = event.data.choices[0].delta
          if delta.content:
              print(delta.content, end="")
  ```

  ```python title="chat.stream_async — async" theme={null}
  res = await client.chat.stream_async(
      model="mistral-small-latest",
      messages=[{"role": "user", "content": "Hello!"}],
  )
  async with res as event_stream:
      async for event in event_stream:
          delta = event.data.choices[0].delta
          if delta.content:
              print(delta.content, end="")
  ```
</CodeGroup>

Both streaming patterns are fully supported with time-to-first-token tracking. The wrapper transparently passes through the SDK's `EventStream` / `EventStreamAsync` context manager, buffers `delta.content` chunks, and emits a single LLM span containing the full reduced output and the final token usage Mistral reports on the terminal chunk.

## Async

The Mistral SDK exposes async via `chat.complete_async` and `chat.stream_async` on the same client class — both are instrumented by `wrap_mistral`. No separate async client class exists.

## Token usage mapping

Mistral already uses our canonical names, so the mapping is the identity:

| Mistral Field       | PandaProbe Field    |
| ------------------- | ------------------- |
| `prompt_tokens`     | `prompt_tokens`     |
| `completion_tokens` | `completion_tokens` |
| `total_tokens`      | `total_tokens`      |