---
id: opentelemetry-instrumentation-mistralai
version: "0.62.3"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# opentelemetry-instrumentation-mistralai — OpenTelemetry Mistral AI instrumentation

License: permissive · Maintenance: active · Downloads: 6.8M/mo

## What it is and what it does

This package is an OpenTelemetry instrumentation plugin that automatically intercepts and traces calls made through the official Mistral AI Python library. Once initialized with a single call to `MistralAiInstrumentor().instrument()`, it captures request and response data as span attributes, giving you visibility into what your LLM application is sending to and receiving from Mistral's endpoints.

By default, it logs prompts, completions, and embeddings to trace spans—useful for debugging and understanding model behavior. However, you can disable this content logging by setting the `TRACELOOP_TRACE_CONTENT` environment variable to `false` if you need to protect sensitive user data or reduce trace size. The instrumentation integrates with your existing OpenTelemetry collector setup, so traces flow into whatever backend you're already using.

Use it for:

- Debug Mistral API calls in development by inspecting prompts and responses in your trace backend
- Monitor production LLM applications to detect latency, errors, or unexpected model behavior
- Correlate Mistral API calls with other application traces for end-to-end request tracing
- Audit what data is being sent to Mistral for compliance or privacy reviews
- Evaluate model output quality by reviewing completions stored in trace spans

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Automatically captures and traces calls to the Mistral AI API using OpenTelemetry, recording request and response data as span attributes for observability and debugging.

Yes, if you are already using OpenTelemetry and the Mistral AI library. Installation is straightforward, maintenance is active, and there are no known vulnerabilities. The permissive Apache-2.0 license poses no barrier. The main consideration is whether your observability stack is already OpenTelemetry-based; if not, you would need to set that up first. Privacy-conscious teams should enable `TRACELOOP_TRACE_CONTENT=false` to avoid logging sensitive prompts.

## Install

pip install opentelemetry-instrumentation-mistralai
uv add opentelemetry-instrumentation-mistralai
poetry add opentelemetry-instrumentation-mistralai

## Installing opentelemetry-instrumentation-mistralai

Before you install: Low friction: pure Python wheel with four stable OpenTelemetry dependencies. Actively maintained as of 2026-08-10 with recent release history.

License in practice: Apache-2.0 permissive license allows use in most projects without significant restrictions.

Quickstart:

pip install opentelemetry-instrumentation-mistralai

from opentelemetry.instrumentation.mistralai import MistralAiInstrumentor

MistralAiInstrumentor().instrument()

Requires Python 3.10 or later. Mistral AI library must be installed separately for instrumentation to attach to actual API calls.

Verify before relying:

- Whether instrumentation works with all Mistral AI endpoints or only a subset
- Performance overhead of tracing on typical Mistral API call latency
- Compatibility with specific versions of the Mistral AI library

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 6.8M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

mistral ai tracing, opentelemetry mistral instrumentation, llm api observability, mistral ai monitoring, trace mistral requests, opentelemetry ai instrumentation, observability, llm-tracing, mistral-ai

[View on SkillFed](https://skillfed.io/packages/opentelemetry-instrumentation-mistralai) · [View on PyPI](https://pypi.org/project/opentelemetry-instrumentation-mistralai/)