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

# Mistral AI

> Trace Mistral AI Python SDK calls with OpenInference and send spans to Arize AX for LLM observability.

[Mistral AI](https://mistral.ai/) provides open-weights and frontier LLMs through the [Mistral Python SDK](https://github.com/mistralai/client-python). Arize AX captures every Mistral SDK call — chat completions, tool calls, embeddings, and token usage — via the [`openinference-instrumentation-mistralai`](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-mistralai) package.

<CardGroup>
  <Card horizontal icon="https://storage.googleapis.com/arize-phoenix-assets/assets/images/phoenix-docs-images/gc.ico" href="http://colab.research.google.com/github/Arize-ai/tutorials/blob/main/python/llm/tracing/mistral/mistral-tracing.ipynb" title="Mistral Tracing Tutorial (Google Colab)" />
</CardGroup>

## Prerequisites

* Python 3.10+
* An Arize AX account ([sign up](https://arize.com/sign-up/))
* A `MISTRAL_API_KEY` from [La Plateforme](https://console.mistral.ai/api-keys)

## Launch Arize AX

1. Sign in to your [Arize AX account](https://app.arize.com/).
2. From **Space Settings**, copy your **Space ID** and **API Key**. You will set them as `ARIZE_SPACE_ID` and `ARIZE_API_KEY` below.

## Install

```bash theme={null}
pip install arize-otel openinference-instrumentation-mistralai mistralai
```

## Configure credentials

```bash theme={null}
export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"
export ARIZE_PROJECT_NAME="mistral-tracing-example"
export MISTRAL_API_KEY="<your-mistral-api-key>"
```

## Setup tracing

```python theme={null}
# instrumentation.py
import os

from arize.otel import register
from openinference.instrumentation.mistralai import MistralAIInstrumentor

tracer_provider = register(
    space_id=os.environ["ARIZE_SPACE_ID"],
    api_key=os.environ["ARIZE_API_KEY"],
    project_name=os.environ["ARIZE_PROJECT_NAME"],
)

MistralAIInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for Mistral AI.")
```

## Run Mistral AI

```python theme={null}
# example.py
import os

# Importing instrumentation first ensures tracing is set up
# before `mistralai` is imported.
from instrumentation import tracer_provider

from mistralai.client import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

response = client.chat.complete(
    model="mistral-small-latest",
    messages=[
        {
            "role": "user",
            "content": "Why is the ocean salty? Answer in two sentences.",
        },
    ],
)

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

### Expected output

```text wrap theme={null}
Arize AX tracing initialized for Mistral AI.
The ocean is salty because rivers continuously dissolve mineral salts from rocks and soil and carry them to the sea, where they accumulate over millions of years. Water leaves the ocean through evaporation but the salts remain, steadily concentrating until reaching today's roughly 3.5% salinity.
```

## Verify in Arize AX

1. Open your Arize AX space and select project **`mistral-tracing-example`**.
2. You should see a new trace within \~30 seconds containing a `MistralClient.chat` LLM span with the prompt, response, and token usage attached.
3. If no traces appear, see [Troubleshooting](#troubleshooting).

## Troubleshooting

* **No traces in Arize AX.** Confirm `ARIZE_SPACE_ID` and `ARIZE_API_KEY` are set in the same shell that runs `example.py`. Enable OpenTelemetry debug logs with `export OTEL_LOG_LEVEL=debug` and re-run.
* **Mistral spans missing but other spans present.** `MistralAIInstrumentor().instrument(...)` must run before any `from mistralai.client import Mistral` import. Make sure `instrumentation.py` is the first import in your entry point.
* **`401` from Mistral.** Verify `MISTRAL_API_KEY` is set and active in [La Plateforme](https://console.mistral.ai/api-keys).
* **`404` for the model.** Mistral occasionally retires older model aliases. If `mistral-small-latest` returns 404, see the [Mistral model list](https://docs.mistral.ai/getting-started/models/models_overview/) and pick a current one.

## Resources

<CardGroup>
  <Card icon="book-open" href="https://docs.mistral.ai/" title="Mistral AI Documentation" horizontal />

  <Card icon="terminal" href="https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-mistralai" title="OpenInference Mistral AI Instrumentor" horizontal />

  <Card icon="github" href="https://github.com/Arize-ai/openinference/blob/main/python/instrumentation/openinference-instrumentation-mistralai/examples/chat_completions.py" title="Mistral Chat Completions Example" horizontal />
</CardGroup>