---
title: "Mistral AI"
description: "Adds instrumentation for the Mistral AI SDK. (default)"
url: https://docs.sentry.io/platforms/javascript/guides/effect/configuration/integrations/mistral/
---

# Mistral AI | Sentry for Effect

Requires SDK version `11.0.0` or higher.

*Import name: `Sentry.mistralAIIntegration`*

This integration is enabled by default when tracing is enabled. If you'd like to modify your default integrations, read [this](https://docs.sentry.io/platforms/javascript/guides/effect/configuration/integrations.md#modifying-default-integrations).

The `mistralAIIntegration` adds instrumentation for the [`@mistralai/mistralai`](https://www.npmjs.com/package/@mistralai/mistralai) SDK to capture [agent tracing](https://docs.sentry.io/platforms/javascript/guides/effect/agent-tracing.md) `gen_ai` spans, recording model, token usage, latency, and (when enabled) inputs and outputs.

```javascript
Sentry.init({
  dsn: "https://<key>@o<orgId>.ingest.sentry.io/<projectId>",
  // Tracing must be enabled for agent tracing to work
  tracesSampleRate: 1.0,
  integrations: [Sentry.mistralAIIntegration()],
});
```

## [Supported Operations](https://docs.sentry.io/platforms/javascript/guides/effect/configuration/integrations/mistral.md#supported-operations)

By default, tracing support is added to the following Mistral AI SDK calls:

* `chat.complete()` / `chat.parse()` - Chat completion requests
* `chat.stream()` / `chat.parseStream()` - Streaming chat completions
* `embeddings.create()` - Embedding requests
* `agents.complete()` - Agent completion requests
* `agents.stream()` - Streaming agent completions

Streaming and non-streaming requests are automatically detected and handled appropriately.

## [Supported Versions](https://docs.sentry.io/platforms/javascript/guides/effect/configuration/integrations/mistral.md#supported-versions)

* `@mistralai/mistralai`: `>=2.0.0 <3`

## [Options](https://docs.sentry.io/platforms/javascript/guides/effect/configuration/integrations/mistral.md#options)

### [`recordInputs`](https://docs.sentry.io/platforms/javascript/guides/effect/configuration/integrations/mistral.md#recordinputs)

*Type: `boolean` (optional)*

Records inputs to Mistral AI SDK calls (such as prompts and messages).

Defaults to `true` if `dataCollection.genAI.inputs` is `true` (which is the default when using `dataCollection`), or if the deprecated `sendDefaultPii` is `true`.

### [`recordOutputs`](https://docs.sentry.io/platforms/javascript/guides/effect/configuration/integrations/mistral.md#recordoutputs)

*Type: `boolean` (optional)*

Records outputs from Mistral AI SDK calls (such as generated text and responses).

Defaults to `true` if `dataCollection.genAI.outputs` is `true` (which is the default when using `dataCollection`), or if the deprecated `sendDefaultPii` is `true`.

```javascript
Sentry.init({
  dsn: "https://<key>@o<orgId>.ingest.sentry.io/<projectId>",
  tracesSampleRate: 1.0,
  integrations: [
    Sentry.mistralAIIntegration({
      recordInputs: true,
      recordOutputs: true,
    }),
  ],
});
```

## [Manual Instrumentation](https://docs.sentry.io/platforms/javascript/guides/effect/configuration/integrations/mistral.md#manual-instrumentation)

*Import name: `Sentry.instrumentMistralAiClient`*

If your application does not use automatic instrumentation, wrap your Mistral client after setting up Sentry. Use the returned client for all Mistral calls.

```javascript
import * as Sentry from "<sdk-package-name>";
```

```javascript
import { Mistral } from "@mistralai/mistralai";

const mistral = new Mistral({ apiKey: "your-mistral-api-key" });
const client = Sentry.instrumentMistralAiClient(mistral, {
  recordInputs: false,
  recordOutputs: false,
});

const response = await client.chat.complete({
  model: "mistral-small-latest",
  messages: [{ role: "user", content: "Hello!" }],
});
```

Use one instrumentation approach for each client. If automatic instrumentation is already active, you don't need to wrap the client.