Shadowgraph
TrendingBuzzResearch
Chrome extension
Sign in

mistralai/client-ts

TS Client library for Mistral AI platform

TypeScript

157

272 commits

updated Oct 9, 2026

See the code

README

Mistral Typescript Client

This is v2 of the Mistral TypeScript SDK.

Key changes from v1: ESM-only, shorter type names, forward-compatible enums/unions, Zod v4. See the Migration Guide for full details.

To pin v1: npm install @mistralai/mistralai@^1 · v1 documentation and source

Summary

Mistral AI API: Our Chat Completion and Embeddings APIs specification. Create your account on La Plateforme to get access and read the docs to learn how to use it.

Table of Contents

SDK Installation

The SDK can be installed with either npm, pnpm, bun or yarn package managers.

NPM

npm add @mistralai/mistralai

PNPM

pnpm add @mistralai/mistralai

Bun

bun add @mistralai/mistralai

Yarn

yarn add @mistralai/mistralai

[!NOTE] This package is published as an ES Module (ESM) only. For applications using CommonJS, use await import("@mistralai/mistralai") to import and use this package.

Requirements

For supported JavaScript runtimes, please consult RUNTIMES.md.

API Key Setup

Before you begin, you will need a Mistral AI API key.

  1. Get your own Mistral API Key: https://docs.mistral.ai/#api-access
  2. Set your Mistral API Key as an environment variable. You only need to do this once.
# set Mistral API Key (using zsh for example)
$ echo 'export MISTRAL_API_KEY=[your_key_here]' >> ~/.zshenv

# reload the environment (or just quit and open a new terminal)
$ source ~/.zshenv

Service-account token

Node workloads with a mounted service-account token can set MISTRAL_SA_TOKEN_PATH instead. The file is re-read on every request, so rotation is picked up. Credentials resolve in this order:

  1. an Authorization header passed per request via headers
  2. new Mistral({ apiKey }), which also accepts an async function
  3. the token at MISTRAL_SA_TOKEN_PATH
  4. MISTRAL_API_KEY

An unreadable or empty token file fails the request with an UnexpectedClientError whose cause explains why.

SDK Example Usage

Create Chat Completions

This example shows how to create chat completions.

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.chat.complete({
    model: "mistral-large-latest",
    messages: [
      {
        role: "user",
        content:
          "Who is the best French painter? Answer in one short sentence.",
      },
    ],
    responseFormat: {
      type: "text",
    },
  });

  console.log(result);
}

run();

Upload a file

This example shows how to upload a file.

import { Mistral } from "@mistralai/mistralai";
import { openAsBlob } from "node:fs";

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.files.upload({
    file: await openAsBlob("example.file"),
  });

  console.log(result);
}

run();

Create Agents Completions

This example shows how to create agents completions.

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.agents.complete({
    messages: [
      {
        role: "user",
        content:
          "Who is the best French painter? Answer in one short sentence.",
      },
    ],
    responseFormat: {
      type: "text",
    },
    agentId: "<id>",
  });

  console.log(result);
}

run();

Create Embedding Request

This example shows how to create embedding request.

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.embeddings.create({
    model: "mistral-embed",
    inputs: [
      "Embed this sentence.",
      "As well as this one.",
    ],
  });

  console.log(result);
}

run();

Providers' SDKs

We have dedicated SDKs for the following providers:

Available Resources and Operations

Available methods

Agents

Audio.Speech

Audio.Transcriptions

  • complete - Create Transcription
  • stream - Create Streaming Transcription (SSE)

Audio.Voices

  • list - List all voices ⚠️ Deprecated Use search instead.
  • create - Create a new voice
  • delete - Delete a custom voice
  • update - Update voice metadata
  • get - Get voice details
  • getSampleAudio - Get voice sample audio
  • search - List voices, cursor-paginated

Batch.Jobs

Beta.Agents

Beta.Connectors

Beta.Conversations

  • start - Create a conversation and append entries to it.
  • list - List all created conversations.
  • get - Retrieve a conversation information.
  • delete - Delete a conversation.
  • append - Append new entries to an existing conversation.
  • getHistory - Retrieve all entries in a conversation.
  • getMessages - Retrieve all messages in a conversation.
  • restart - Restart a conversation starting from a given entry.
  • startStream - Create a conversation and append entries to it.
  • appendStream - Append new entries to an existing conversation.
  • restartStream - Restart a conversation starting from a given entry.

Beta.Libraries

  • list - List all libraries you have access to.
  • create - Create a new Library.
  • get - Detailed information about a specific Library.
  • delete - Delete a library and all of it's document.
  • update - Update a library.
  • librariesUpdateV1 - Update a library. ⚠️ Deprecated

Beta.Libraries.Accesses

  • list - List all of the access to this library.
  • updateOrCreate - Create or update an access level.
  • delete - Delete an access level.

Beta.Libraries.Documents

  • list - List documents in a given library.
  • upload - Upload a new document.
  • get - Retrieve the metadata of a specific document.
  • update - Update the metadata of a specific document.
  • librariesDocumentsUpdateV1 - Update the metadata of a specific document. ⚠️ Deprecated
  • delete - Delete a document.
  • textContent - Retrieve the text content of a specific document.
  • status - Retrieve the processing status of a specific document.
  • getSignedUrl - Retrieve the signed URL of a specific document.
  • extractedTextSignedUrl - Retrieve the signed URL of text extracted from a given document.
  • reprocess - Reprocess a document.

Beta.Observability.Datasets

  • create - Create a new empty dataset
  • list - List existing datasets
  • fetch - Get dataset by ID or slug
  • delete - Delete a dataset
  • update - Patch dataset
  • listRecords - List existing records in the dataset
  • createRecord - Add a record to the dataset
  • importFromFile - Populate the dataset with records from an uploaded file
  • importFromPlayground - Populate the dataset with records from playground conversations
  • importFromSpans - Populate the dataset with records mapped from telemetry spans
  • importFromDatasetRecords - Populate the dataset with records from another dataset
  • exportToJsonl - Export to the Files API and retrieve presigned URL to download the resulting JSONL file
  • fetchTask - Get status of a dataset import task
  • listTasks - List import tasks for the given dataset

Beta.Observability.Datasets.Records

  • fetch - Get the content of a given dataset record
  • delete - Delete a record from a dataset
  • bulkDelete - Delete multiple records from datasets
  • judge - Run Judge on a dataset record based on the given options
  • updatePayload - Update a dataset record payload
  • updateProperties - Update dataset record properties

Beta.Observability.Evaluations

Beta.Observability.Evaluations.Optimizations

  • list - List optimizations with optional filters
  • get - Get an optimization by id (with its anchored evaluation + project)
  • listTrials - List an optimization's trials with their observation runs (paginated)

Beta.Observability.Evaluations.Projects

  • list - List projects
  • get - Get project by slug

Beta.Observability.Evaluations.Records

  • get - Get a specific record from an evaluation run
  • search - Search records for an evaluation run with content filters

Beta.Observability.Evaluations.Runs

  • search - Search evaluation runs with filters
  • searchAll - Search evaluation runs across all evaluations
  • get - Get a specific evaluation run by ID
  • getStatistics - Get statistics for a specific evaluation run
  • computeStatistics - Compute statistics for a specific evaluation run with optional filters

Beta.Observability.Judges

Beta.Observability.Logs

Beta.Observability.Spans

Beta.Observability.Traces

Beta.Prompts

Beta.Rag.IngestionPipelineConfigurations

Beta.Rag.ManagedIndexes

  • create - Create a managed index
  • list - List managed indexes
  • get - Get a managed index
  • update - Update a managed index schema
  • delete - Delete a managed index
  • ingestDocuments - Ingest documents into a managed index
  • deleteDocuments - Delete documents from a managed index
  • search - Search a managed index
  • navigate - Navigate to adjacent chunks
  • read - Read chunks within a span
  • grep - Grep for a pattern within a source
  • getChunk - Get a single chunk by id

Beta.Rag.SearchIndexes

Beta.ServiceAccounts

Beta.Skills

Beta.Users

Chat

Classifiers

Embeddings

Events

Files

Fim

Models

Ocr

Realtime.Sessions

  • create - Create Client Session

Workflows

Workflows.Deployments

Workflows.Events

Workflows.Executions

Workflows.Metrics

Workflows.Runs

Workflows.Schedules

Server-sent event streaming

Server-sent events are used to stream content from certain operations. These operations will expose the stream as an async iterable that can be consumed using a for await...of loop. The loop will terminate when the server no longer has any events to send and closes the underlying connection.

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.conversations.startStream({
    inputs: [
      {
        object: "entry",
        type: "agent.handoff",
        previousAgentId: "<id>",
        previousAgentName: "<value>",
        nextAgentId: "<id>",
        nextAgentName: "<value>",
      },
    ],
    completionArgs: {
      responseFormat: {
        type: "text",
      },
    },
  });

  for await (const event of result) {
    console.log(event);
  }
}

run();

Pagination

Some of the endpoints in this SDK support pagination. To use pagination, you make your SDK calls as usual, but the returned response object will also be an async iterable that can be consumed using the for await...of syntax.

Here's an example of one such pagination call:

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

File uploads

Certain SDK methods accept files as part of a multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.

[!TIP]

Depending on your JavaScript runtime, there are convenient utilities that return a handle to a file without reading the entire contents into memory:

  • Node.js v20+: Since v20, Node.js comes with a native openAsBlob function in node:fs.
  • Bun: The native Bun.file function produces a file handle that can be used for streaming file uploads.
  • Browsers: All supported browsers return an instance to a File when reading the value from an <input type="file"> element.
  • Node.js v18: A file stream can be created using the fileFrom helper from fetch-blob/from.js.
import { Mistral } from "@mistralai/mistralai";
import { openAsBlob } from "node:fs";

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.libraries.documents.upload({
    libraryId: "a02150d9-5ee0-4877-b62c-28b1fcdf3b76",
    requestBody: {
      file: await openAsBlob("example.file"),
    },
  });

  console.log(result);
}

run();

Retries

Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.

To change the default retry strategy for a single API call, simply provide a retryConfig object to the call:

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list(undefined, {
    retries: {
      strategy: "backoff",
      backoff: {
        initialInterval: 1,
        maxInterval: 50,
        exponent: 1.1,
        maxElapsedTime: 100,
      },
      retryConnectionErrors: false,
    },
  });

  for await (const page of result) {
    console.log(page);
  }
}

run();

If you'd like to override the default retry strategy for all operations that support retries, you can provide a retryConfig at SDK initialization:

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

const mistral = new Mistral({
  retryConfig: {
    strategy: "backoff",
    backoff: {
      initialInterval: 1,
      maxInterval: 50,
      exponent: 1.1,
      maxElapsedTime: 100,
    },
    retryConnectionErrors: false,
  },
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

Error Handling

MistralError is the base class for all HTTP error responses. It has the following properties:

PropertyTypeDescription
error.messagestringError message
error.statusCodenumberHTTP response status code eg 404
error.headersHeadersHTTP response headers
error.bodystringHTTP body. Can be empty string if no body is returned.
error.rawResponseResponseRaw HTTP response
error.data$Optional. Some errors may contain structured data. See Error Classes.

Example

import { Mistral } from "@mistralai/mistralai";
import * as errors from "@mistralai/mistralai/models/errors";

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  try {
    const result = await mistral.beta.serviceAccounts.create({
      name: "<value>",
      workspaceId: "cf2146d0-158c-4b19-b8b1-ca0c68f41143",
    });

    console.log(result);
  } catch (error) {
    // The base class for HTTP error responses
    if (error instanceof errors.MistralError) {
      console.log(error.message);
      console.log(error.statusCode);
      console.log(error.body);
      console.log(error.headers);

      // Depending on the method different errors may be thrown
      if (error instanceof errors.HTTPValidationError) {
        console.log(error.data$.detail); // ValidationError[]
      }
    }
  }
}

run();

Error Classes

Primary error:

Less common errors (8)

Network errors:

Inherit from MistralError:

  • HTTPValidationError: Validation Error. Status code 422. Applicable to 165 of 278 methods.*
  • ObservabilityError: Bad Request - Invalid request parameters or data. Applicable to 69 of 278 methods.*
  • ResponseValidationError: Type mismatch between the data returned from the server and the structure expected by the SDK. See error.rawValue for the raw value and error.pretty() for a nicely formatted multi-line string.

* Check the method documentation to see if the error is applicable.

Server Selection

Select Server by Name

You can override the default server globally by passing a server name to the server: keyof typeof ServerList optional parameter when initializing the SDK client instance. The selected server will then be used as the default on the operations that use it. This table lists the names associated with the available servers:

NameServerDescription
globalhttps://api.mistral.aiGlobal Production server
euhttps://api.eu.mistral.aiEU Production server
ushttps://api.us.mistral.aiUS Production server

Example

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

const mistral = new Mistral({
  server: "global",
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

Override Server URL Per-Client

The default server can also be overridden globally by passing a URL to the serverURL: string optional parameter when initializing the SDK client instance. For example:

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

const mistral = new Mistral({
  serverURL: "https://api.mistral.ai",
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

Custom HTTP Client

The TypeScript SDK makes API calls using an HTTPClient that wraps the native Fetch API. This client is a thin wrapper around fetch and provides the ability to attach hooks around the request lifecycle that can be used to modify the request or handle errors and response.

The HTTPClient constructor takes an optional fetcher argument that can be used to integrate a third-party HTTP client or when writing tests to mock out the HTTP client and feed in fixtures.

The following example shows how to:

  • route requests through a proxy server using undici's ProxyAgent
  • use the "beforeRequest" hook to add a custom header and a timeout to requests
  • use the "requestError" hook to log errors
import { Mistral } from "@mistralai/mistralai";
import { ProxyAgent } from "undici";
import { HTTPClient } from "@mistralai/mistralai/lib/http";

const dispatcher = new ProxyAgent("http://proxy.example.com:8080");

const httpClient = new HTTPClient({
  // 'fetcher' takes a function that has the same signature as native 'fetch'.
  fetcher: (input, init) =>
    // 'dispatcher' is specific to undici and not part of the standard Fetch API.
    fetch(input, { ...init, dispatcher } as RequestInit),
});

httpClient.addHook("beforeRequest", (request) => {
  const nextRequest = new Request(request, {
    signal: request.signal || AbortSignal.timeout(5000)
  });

  nextRequest.headers.set("x-custom-header", "custom value");

  return nextRequest;
});

httpClient.addHook("requestError", (error, request) => {
  console.group("Request Error");
  console.log("Reason:", `${error}`);
  console.log("Endpoint:", `${request.method} ${request.url}`);
  console.groupEnd();
});

const sdk = new Mistral({ httpClient: httpClient });

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

NameTypeSchemeEnvironment Variable
apiKeyhttpHTTP BearerMISTRAL_API_KEY

To authenticate with the API the apiKey parameter must be set when initializing the SDK client instance. For example:

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

Per-Operation Security Schemes

Some operations in this SDK require the security scheme to be specified at the request level. For example:

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

const mistral = new Mistral();

async function run() {
  const result = await mistral.beta.users.getIdentity({});

  console.log(result);
}

run();

Standalone functions

All the methods listed above are available as standalone functions. These functions are ideal for use in applications running in the browser, serverless runtimes or other environments where application bundle size is a primary concern. When using a bundler to build your application, all unused functionality will be either excluded from the final bundle or tree-shaken away.

To read more about standalone functions, check FUNCTIONS.md.

Available standalone functions

Debugging

You can setup your SDK to emit debug logs for SDK requests and responses.

You can pass a logger that matches console's interface as an SDK option.

[!WARNING] Beware that debug logging will reveal secrets, like API tokens in headers, in log messages printed to a console or files. It's recommended to use this feature only during local development and not in production.

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

const sdk = new Mistral({ debugLogger: console });

You can also enable a default debug logger by setting an environment variable MISTRAL_DEBUG to true.

Telemetry & Observability

The SDK can emit OpenTelemetry traces for the API calls it makes (chat, agents, embeddings, OCR, …), following the GenAI semantic conventions. Spans capture the operation, model, token usage, and — unless redacted — the input/output messages and tool calls. Telemetry is opt-in and lives in the @mistralai/mistralai/extra/observability module.

Installation

Dedicated mode loads the OpenTelemetry SDK and OTLP exporter on demand. Install them alongside the client:

npm install @opentelemetry/sdk-trace-base @opentelemetry/exporter-trace-otlp-http @opentelemetry/resources

Enabling telemetry

Either set an environment variable before creating the client:

export MISTRAL_SDK_TELEMETRY=dedicated   # dedicated | global | false

or configure it in code:

import { Mistral } from "@mistralai/mistralai";
import { configureTelemetry } from "@mistralai/mistralai/extra/observability";

const client = new Mistral({ apiKey: process.env["MISTRAL_API_KEY"] });

// Dedicated mode (default): the SDK creates and owns an OTLP exporter that ships
// spans to the Mistral telemetry endpoint. Spans are redacted before export.
await configureTelemetry(client);

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

Provider modes

configureTelemetry(client, provider) selects where spans go and who owns the export pipeline:

providerWho owns the exporterWhere spans goRedaction
"dedicated" (default)The SDKMistral telemetry endpointApplied automatically
"global"Your applicationYour global OpenTelemetry providerNot applied — you need to wrap your own exporter
a TracerProviderYour applicationThe provider you passNot applied — you need to wrap your own exporter

In global/custom modes your application owns the pipeline, so the redaction option is ignored (a warning is logged). Wrap your own exporter with RedactingSpanExporter to redact spans there:

import { trace } from "@opentelemetry/api";
import { OTLPTraceExporter } from "@opentelemetry/exporter-trace-otlp-http";
import { BasicTracerProvider, BatchSpanProcessor } from "@opentelemetry/sdk-trace-base";
import { Mistral } from "@mistralai/mistralai";
import { configureTelemetry, RedactingSpanExporter } from "@mistralai/mistralai/extra/observability";

const provider = new BasicTracerProvider({
  spanProcessors: [
    new BatchSpanProcessor(new RedactingSpanExporter(new OTLPTraceExporter())),
  ],
});
trace.setGlobalTracerProvider(provider);

const client = new Mistral({ apiKey: process.env["MISTRAL_API_KEY"] });

// SDK spans now flow through your global provider (already redacted above).
await configureTelemetry(client, "global");

Redaction

In dedicated mode, redaction is on by default. Control it with the redaction option, which also accepts any of the reusable policies from @mistralai/mistralai/extra/observability:

import { AttributeRedactionPolicy } from "@mistralai/mistralai/extra/observability";

await configureTelemetry(client);                                                            // default policy (regex)
await configureTelemetry(client, "dedicated", { redaction: new AttributeRedactionPolicy() }); // very conservative key-oriented policy
await configureTelemetry(client, "dedicated", { redaction: false });                          // disabled - no redaction
await configureTelemetry(client, "dedicated", {                                               // custom callback to control how attributes get redacted
  redaction: (key, value) => (key.includes("email") ? undefined : value),
});
PolicyStrategyTrade-off
RegexRedactionPolicy (default, redaction: true)Content-oriented: keeps keys and structure, redacts matched substrings (secret tokens plus PII — emails, card-like sequences, IPv4).Redacts most sensitive data while preserving observability value; may miss free-form PII or secrets not in the pattern set.
AttributeRedactionPolicyKey-oriented: redacts whole values for sensitive keys (explicit set, fragment match, or non-primitive value), then scans kept values for secret token patterns.Very conservative, but erases most prompt/response content.
CallbackRedactionPolicy (redaction: <callback>)Your (key, value) => value | undefined masker per attribute; return undefined to drop the attribute.Full control; you own the logic.

The built-in defaults are exported as constants, so you can extend them instead of replacing them wholesale:

import {
  AttributeRedactionPolicy,
  DEFAULT_PII_SECRET_PATTERNS,
  DEFAULT_SENSITIVE_ATTRIBUTE_KEYS,
  RegexRedactionPolicy,
  configureTelemetry,
} from "@mistralai/mistralai/extra/observability";

// Content-oriented: add a custom secret pattern to the default set.
await configureTelemetry(client, "dedicated", {
  redaction: new RegexRedactionPolicy([...DEFAULT_PII_SECRET_PATTERNS, /\bacme-[a-z0-9]{16}\b/g]),
});

// Key-oriented: mask an extra application attribute on top of the defaults.
await configureTelemetry(client, "dedicated", {
  redaction: new AttributeRedactionPolicy({
    sensitiveKeys: new Set([...DEFAULT_SENSITIVE_ATTRIBUTE_KEYS, "app.customer.email"]),
  }),
});

Note: the RedactingSpanExporter primitive is reusable by any OpenTelemetry application, independent of the Mistral client.

Environment variables

VariableDescriptionDefault
MISTRAL_SDK_TELEMETRYAuto-enable telemetry: dedicated, global, or false.unset (disabled)
MISTRAL_OTLP_TRACES_ENDPOINTOverride the OTLP traces endpoint used in dedicated mode.https://api.mistral.ai/telemetry/v1/traces
MISTRAL_API_KEYUsed as the bearer token for the dedicated-mode exporter.—

Runnable examples live in examples/src/observability.

Development

Contributions

While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.

Project health

npm

@mistralai/mistralai

Latest release

2.7.0 · Sep 9, 2026

Releases this year

23

Significant stargazers

Arnaud Benhamdine

56 followers · starred Mar 2025

Murtuzaali Surti

171 followers · starred Dec 2024

Martin Oppitz

51 followers · starred Mar 2026

Otto Sulin

89 followers · starred Jan 2026

Similar repos

mistralai/client-python

Python client library for Mistral AI platform

773

same org

mistralai/mistral-vibe

Minimal CLI coding agent by Mistral

5,105

same org

mistralai/cookbook

2,341

same org

openai/openai-node

Official JavaScript / TypeScript library for the OpenAI API

11,217

meta-llama/llama-api-typescript

The official Typescript library for the Llama API

38

groq/groq-typescript

The official Node.js / Typescript library for the Groq API

266

codeany-ai/open-agent-sdk-typescript

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

2,745

googleapis/js-genai

TypeScript/JavaScript SDK for Gemini and Vertex AI.

1,690

mistralai/client-ts

TS Client library for Mistral AI platform

TypeScript

157

272 commits

updated Oct 9, 2026

See the code

README

Mistral Typescript Client

This is v2 of the Mistral TypeScript SDK.

Key changes from v1: ESM-only, shorter type names, forward-compatible enums/unions, Zod v4. See the Migration Guide for full details.

To pin v1: npm install @mistralai/mistralai@^1 · v1 documentation and source

Summary

Mistral AI API: Our Chat Completion and Embeddings APIs specification. Create your account on La Plateforme to get access and read the docs to learn how to use it.

Table of Contents

SDK Installation

The SDK can be installed with either npm, pnpm, bun or yarn package managers.

NPM

npm add @mistralai/mistralai

PNPM

pnpm add @mistralai/mistralai

Bun

bun add @mistralai/mistralai

Yarn

yarn add @mistralai/mistralai

[!NOTE] This package is published as an ES Module (ESM) only. For applications using CommonJS, use await import("@mistralai/mistralai") to import and use this package.

Requirements

For supported JavaScript runtimes, please consult RUNTIMES.md.

API Key Setup

Before you begin, you will need a Mistral AI API key.

  1. Get your own Mistral API Key: https://docs.mistral.ai/#api-access
  2. Set your Mistral API Key as an environment variable. You only need to do this once.
# set Mistral API Key (using zsh for example)
$ echo 'export MISTRAL_API_KEY=[your_key_here]' >> ~/.zshenv

# reload the environment (or just quit and open a new terminal)
$ source ~/.zshenv

Service-account token

Node workloads with a mounted service-account token can set MISTRAL_SA_TOKEN_PATH instead. The file is re-read on every request, so rotation is picked up. Credentials resolve in this order:

  1. an Authorization header passed per request via headers
  2. new Mistral({ apiKey }), which also accepts an async function
  3. the token at MISTRAL_SA_TOKEN_PATH
  4. MISTRAL_API_KEY

An unreadable or empty token file fails the request with an UnexpectedClientError whose cause explains why.

SDK Example Usage

Create Chat Completions

This example shows how to create chat completions.

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.chat.complete({
    model: "mistral-large-latest",
    messages: [
      {
        role: "user",
        content:
          "Who is the best French painter? Answer in one short sentence.",
      },
    ],
    responseFormat: {
      type: "text",
    },
  });

  console.log(result);
}

run();

Upload a file

This example shows how to upload a file.

import { Mistral } from "@mistralai/mistralai";
import { openAsBlob } from "node:fs";

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.files.upload({
    file: await openAsBlob("example.file"),
  });

  console.log(result);
}

run();

Create Agents Completions

This example shows how to create agents completions.

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.agents.complete({
    messages: [
      {
        role: "user",
        content:
          "Who is the best French painter? Answer in one short sentence.",
      },
    ],
    responseFormat: {
      type: "text",
    },
    agentId: "<id>",
  });

  console.log(result);
}

run();

Create Embedding Request

This example shows how to create embedding request.

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.embeddings.create({
    model: "mistral-embed",
    inputs: [
      "Embed this sentence.",
      "As well as this one.",
    ],
  });

  console.log(result);
}

run();

Providers' SDKs

We have dedicated SDKs for the following providers:

Available Resources and Operations

Available methods

Agents

Audio.Speech

Audio.Transcriptions

  • complete - Create Transcription
  • stream - Create Streaming Transcription (SSE)

Audio.Voices

  • list - List all voices ⚠️ Deprecated Use search instead.
  • create - Create a new voice
  • delete - Delete a custom voice
  • update - Update voice metadata
  • get - Get voice details
  • getSampleAudio - Get voice sample audio
  • search - List voices, cursor-paginated

Batch.Jobs

Beta.Agents

Beta.Connectors

Beta.Conversations

  • start - Create a conversation and append entries to it.
  • list - List all created conversations.
  • get - Retrieve a conversation information.
  • delete - Delete a conversation.
  • append - Append new entries to an existing conversation.
  • getHistory - Retrieve all entries in a conversation.
  • getMessages - Retrieve all messages in a conversation.
  • restart - Restart a conversation starting from a given entry.
  • startStream - Create a conversation and append entries to it.
  • appendStream - Append new entries to an existing conversation.
  • restartStream - Restart a conversation starting from a given entry.

Beta.Libraries

  • list - List all libraries you have access to.
  • create - Create a new Library.
  • get - Detailed information about a specific Library.
  • delete - Delete a library and all of it's document.
  • update - Update a library.
  • librariesUpdateV1 - Update a library. ⚠️ Deprecated

Beta.Libraries.Accesses

  • list - List all of the access to this library.
  • updateOrCreate - Create or update an access level.
  • delete - Delete an access level.

Beta.Libraries.Documents

  • list - List documents in a given library.
  • upload - Upload a new document.
  • get - Retrieve the metadata of a specific document.
  • update - Update the metadata of a specific document.
  • librariesDocumentsUpdateV1 - Update the metadata of a specific document. ⚠️ Deprecated
  • delete - Delete a document.
  • textContent - Retrieve the text content of a specific document.
  • status - Retrieve the processing status of a specific document.
  • getSignedUrl - Retrieve the signed URL of a specific document.
  • extractedTextSignedUrl - Retrieve the signed URL of text extracted from a given document.
  • reprocess - Reprocess a document.

Beta.Observability.Datasets

  • create - Create a new empty dataset
  • list - List existing datasets
  • fetch - Get dataset by ID or slug
  • delete - Delete a dataset
  • update - Patch dataset
  • listRecords - List existing records in the dataset
  • createRecord - Add a record to the dataset
  • importFromFile - Populate the dataset with records from an uploaded file
  • importFromPlayground - Populate the dataset with records from playground conversations
  • importFromSpans - Populate the dataset with records mapped from telemetry spans
  • importFromDatasetRecords - Populate the dataset with records from another dataset
  • exportToJsonl - Export to the Files API and retrieve presigned URL to download the resulting JSONL file
  • fetchTask - Get status of a dataset import task
  • listTasks - List import tasks for the given dataset

Beta.Observability.Datasets.Records

  • fetch - Get the content of a given dataset record
  • delete - Delete a record from a dataset
  • bulkDelete - Delete multiple records from datasets
  • judge - Run Judge on a dataset record based on the given options
  • updatePayload - Update a dataset record payload
  • updateProperties - Update dataset record properties

Beta.Observability.Evaluations

Beta.Observability.Evaluations.Optimizations

  • list - List optimizations with optional filters
  • get - Get an optimization by id (with its anchored evaluation + project)
  • listTrials - List an optimization's trials with their observation runs (paginated)

Beta.Observability.Evaluations.Projects

  • list - List projects
  • get - Get project by slug

Beta.Observability.Evaluations.Records

  • get - Get a specific record from an evaluation run
  • search - Search records for an evaluation run with content filters

Beta.Observability.Evaluations.Runs

  • search - Search evaluation runs with filters
  • searchAll - Search evaluation runs across all evaluations
  • get - Get a specific evaluation run by ID
  • getStatistics - Get statistics for a specific evaluation run
  • computeStatistics - Compute statistics for a specific evaluation run with optional filters

Beta.Observability.Judges

Beta.Observability.Logs

Beta.Observability.Spans

Beta.Observability.Traces

Beta.Prompts

Beta.Rag.IngestionPipelineConfigurations

Beta.Rag.ManagedIndexes

  • create - Create a managed index
  • list - List managed indexes
  • get - Get a managed index
  • update - Update a managed index schema
  • delete - Delete a managed index
  • ingestDocuments - Ingest documents into a managed index
  • deleteDocuments - Delete documents from a managed index
  • search - Search a managed index
  • navigate - Navigate to adjacent chunks
  • read - Read chunks within a span
  • grep - Grep for a pattern within a source
  • getChunk - Get a single chunk by id

Beta.Rag.SearchIndexes

Beta.ServiceAccounts

Beta.Skills

Beta.Users

Chat

Classifiers

Embeddings

Events

Files

Fim

Models

Ocr

Realtime.Sessions

  • create - Create Client Session

Workflows

Workflows.Deployments

Workflows.Events

Workflows.Executions

Workflows.Metrics

Workflows.Runs

Workflows.Schedules

Server-sent event streaming

Server-sent events are used to stream content from certain operations. These operations will expose the stream as an async iterable that can be consumed using a for await...of loop. The loop will terminate when the server no longer has any events to send and closes the underlying connection.

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.conversations.startStream({
    inputs: [
      {
        object: "entry",
        type: "agent.handoff",
        previousAgentId: "<id>",
        previousAgentName: "<value>",
        nextAgentId: "<id>",
        nextAgentName: "<value>",
      },
    ],
    completionArgs: {
      responseFormat: {
        type: "text",
      },
    },
  });

  for await (const event of result) {
    console.log(event);
  }
}

run();

Pagination

Some of the endpoints in this SDK support pagination. To use pagination, you make your SDK calls as usual, but the returned response object will also be an async iterable that can be consumed using the for await...of syntax.

Here's an example of one such pagination call:

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

File uploads

Certain SDK methods accept files as part of a multi-part request. It is possible and typically recommended to upload files as a stream rather than reading the entire contents into memory. This avoids excessive memory consumption and potentially crashing with out-of-memory errors when working with very large files. The following example demonstrates how to attach a file stream to a request.

[!TIP]

Depending on your JavaScript runtime, there are convenient utilities that return a handle to a file without reading the entire contents into memory:

  • Node.js v20+: Since v20, Node.js comes with a native openAsBlob function in node:fs.
  • Bun: The native Bun.file function produces a file handle that can be used for streaming file uploads.
  • Browsers: All supported browsers return an instance to a File when reading the value from an <input type="file"> element.
  • Node.js v18: A file stream can be created using the fileFrom helper from fetch-blob/from.js.
import { Mistral } from "@mistralai/mistralai";
import { openAsBlob } from "node:fs";

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.libraries.documents.upload({
    libraryId: "a02150d9-5ee0-4877-b62c-28b1fcdf3b76",
    requestBody: {
      file: await openAsBlob("example.file"),
    },
  });

  console.log(result);
}

run();

Retries

Some of the endpoints in this SDK support retries. If you use the SDK without any configuration, it will fall back to the default retry strategy provided by the API. However, the default retry strategy can be overridden on a per-operation basis, or across the entire SDK.

To change the default retry strategy for a single API call, simply provide a retryConfig object to the call:

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list(undefined, {
    retries: {
      strategy: "backoff",
      backoff: {
        initialInterval: 1,
        maxInterval: 50,
        exponent: 1.1,
        maxElapsedTime: 100,
      },
      retryConnectionErrors: false,
    },
  });

  for await (const page of result) {
    console.log(page);
  }
}

run();

If you'd like to override the default retry strategy for all operations that support retries, you can provide a retryConfig at SDK initialization:

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

const mistral = new Mistral({
  retryConfig: {
    strategy: "backoff",
    backoff: {
      initialInterval: 1,
      maxInterval: 50,
      exponent: 1.1,
      maxElapsedTime: 100,
    },
    retryConnectionErrors: false,
  },
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

Error Handling

MistralError is the base class for all HTTP error responses. It has the following properties:

PropertyTypeDescription
error.messagestringError message
error.statusCodenumberHTTP response status code eg 404
error.headersHeadersHTTP response headers
error.bodystringHTTP body. Can be empty string if no body is returned.
error.rawResponseResponseRaw HTTP response
error.data$Optional. Some errors may contain structured data. See Error Classes.

Example

import { Mistral } from "@mistralai/mistralai";
import * as errors from "@mistralai/mistralai/models/errors";

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  try {
    const result = await mistral.beta.serviceAccounts.create({
      name: "<value>",
      workspaceId: "cf2146d0-158c-4b19-b8b1-ca0c68f41143",
    });

    console.log(result);
  } catch (error) {
    // The base class for HTTP error responses
    if (error instanceof errors.MistralError) {
      console.log(error.message);
      console.log(error.statusCode);
      console.log(error.body);
      console.log(error.headers);

      // Depending on the method different errors may be thrown
      if (error instanceof errors.HTTPValidationError) {
        console.log(error.data$.detail); // ValidationError[]
      }
    }
  }
}

run();

Error Classes

Primary error:

Less common errors (8)

Network errors:

Inherit from MistralError:

  • HTTPValidationError: Validation Error. Status code 422. Applicable to 165 of 278 methods.*
  • ObservabilityError: Bad Request - Invalid request parameters or data. Applicable to 69 of 278 methods.*
  • ResponseValidationError: Type mismatch between the data returned from the server and the structure expected by the SDK. See error.rawValue for the raw value and error.pretty() for a nicely formatted multi-line string.

* Check the method documentation to see if the error is applicable.

Server Selection

Select Server by Name

You can override the default server globally by passing a server name to the server: keyof typeof ServerList optional parameter when initializing the SDK client instance. The selected server will then be used as the default on the operations that use it. This table lists the names associated with the available servers:

NameServerDescription
globalhttps://api.mistral.aiGlobal Production server
euhttps://api.eu.mistral.aiEU Production server
ushttps://api.us.mistral.aiUS Production server

Example

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

const mistral = new Mistral({
  server: "global",
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

Override Server URL Per-Client

The default server can also be overridden globally by passing a URL to the serverURL: string optional parameter when initializing the SDK client instance. For example:

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

const mistral = new Mistral({
  serverURL: "https://api.mistral.ai",
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

Custom HTTP Client

The TypeScript SDK makes API calls using an HTTPClient that wraps the native Fetch API. This client is a thin wrapper around fetch and provides the ability to attach hooks around the request lifecycle that can be used to modify the request or handle errors and response.

The HTTPClient constructor takes an optional fetcher argument that can be used to integrate a third-party HTTP client or when writing tests to mock out the HTTP client and feed in fixtures.

The following example shows how to:

  • route requests through a proxy server using undici's ProxyAgent
  • use the "beforeRequest" hook to add a custom header and a timeout to requests
  • use the "requestError" hook to log errors
import { Mistral } from "@mistralai/mistralai";
import { ProxyAgent } from "undici";
import { HTTPClient } from "@mistralai/mistralai/lib/http";

const dispatcher = new ProxyAgent("http://proxy.example.com:8080");

const httpClient = new HTTPClient({
  // 'fetcher' takes a function that has the same signature as native 'fetch'.
  fetcher: (input, init) =>
    // 'dispatcher' is specific to undici and not part of the standard Fetch API.
    fetch(input, { ...init, dispatcher } as RequestInit),
});

httpClient.addHook("beforeRequest", (request) => {
  const nextRequest = new Request(request, {
    signal: request.signal || AbortSignal.timeout(5000)
  });

  nextRequest.headers.set("x-custom-header", "custom value");

  return nextRequest;
});

httpClient.addHook("requestError", (error, request) => {
  console.group("Request Error");
  console.log("Reason:", `${error}`);
  console.log("Endpoint:", `${request.method} ${request.url}`);
  console.groupEnd();
});

const sdk = new Mistral({ httpClient: httpClient });

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

NameTypeSchemeEnvironment Variable
apiKeyhttpHTTP BearerMISTRAL_API_KEY

To authenticate with the API the apiKey parameter must be set when initializing the SDK client instance. For example:

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

const mistral = new Mistral({
  apiKey: process.env["MISTRAL_API_KEY"] ?? "",
});

async function run() {
  const result = await mistral.beta.prompts.list();

  for await (const page of result) {
    console.log(page);
  }
}

run();

Per-Operation Security Schemes

Some operations in this SDK require the security scheme to be specified at the request level. For example:

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

const mistral = new Mistral();

async function run() {
  const result = await mistral.beta.users.getIdentity({});

  console.log(result);
}

run();

Standalone functions

All the methods listed above are available as standalone functions. These functions are ideal for use in applications running in the browser, serverless runtimes or other environments where application bundle size is a primary concern. When using a bundler to build your application, all unused functionality will be either excluded from the final bundle or tree-shaken away.

To read more about standalone functions, check FUNCTIONS.md.

Available standalone functions

Debugging

You can setup your SDK to emit debug logs for SDK requests and responses.

You can pass a logger that matches console's interface as an SDK option.

[!WARNING] Beware that debug logging will reveal secrets, like API tokens in headers, in log messages printed to a console or files. It's recommended to use this feature only during local development and not in production.

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

const sdk = new Mistral({ debugLogger: console });

You can also enable a default debug logger by setting an environment variable MISTRAL_DEBUG to true.

Telemetry & Observability

The SDK can emit OpenTelemetry traces for the API calls it makes (chat, agents, embeddings, OCR, …), following the GenAI semantic conventions. Spans capture the operation, model, token usage, and — unless redacted — the input/output messages and tool calls. Telemetry is opt-in and lives in the @mistralai/mistralai/extra/observability module.

Installation

Dedicated mode loads the OpenTelemetry SDK and OTLP exporter on demand. Install them alongside the client:

npm install @opentelemetry/sdk-trace-base @opentelemetry/exporter-trace-otlp-http @opentelemetry/resources

Enabling telemetry

Either set an environment variable before creating the client:

export MISTRAL_SDK_TELEMETRY=dedicated   # dedicated | global | false

or configure it in code:

import { Mistral } from "@mistralai/mistralai";
import { configureTelemetry } from "@mistralai/mistralai/extra/observability";

const client = new Mistral({ apiKey: process.env["MISTRAL_API_KEY"] });

// Dedicated mode (default): the SDK creates and owns an OTLP exporter that ships
// spans to the Mistral telemetry endpoint. Spans are redacted before export.
await configureTelemetry(client);

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

Provider modes

configureTelemetry(client, provider) selects where spans go and who owns the export pipeline:

providerWho owns the exporterWhere spans goRedaction
"dedicated" (default)The SDKMistral telemetry endpointApplied automatically
"global"Your applicationYour global OpenTelemetry providerNot applied — you need to wrap your own exporter
a TracerProviderYour applicationThe provider you passNot applied — you need to wrap your own exporter

In global/custom modes your application owns the pipeline, so the redaction option is ignored (a warning is logged). Wrap your own exporter with RedactingSpanExporter to redact spans there:

import { trace } from "@opentelemetry/api";
import { OTLPTraceExporter } from "@opentelemetry/exporter-trace-otlp-http";
import { BasicTracerProvider, BatchSpanProcessor } from "@opentelemetry/sdk-trace-base";
import { Mistral } from "@mistralai/mistralai";
import { configureTelemetry, RedactingSpanExporter } from "@mistralai/mistralai/extra/observability";

const provider = new BasicTracerProvider({
  spanProcessors: [
    new BatchSpanProcessor(new RedactingSpanExporter(new OTLPTraceExporter())),
  ],
});
trace.setGlobalTracerProvider(provider);

const client = new Mistral({ apiKey: process.env["MISTRAL_API_KEY"] });

// SDK spans now flow through your global provider (already redacted above).
await configureTelemetry(client, "global");

Redaction

In dedicated mode, redaction is on by default. Control it with the redaction option, which also accepts any of the reusable policies from @mistralai/mistralai/extra/observability:

import { AttributeRedactionPolicy } from "@mistralai/mistralai/extra/observability";

await configureTelemetry(client);                                                            // default policy (regex)
await configureTelemetry(client, "dedicated", { redaction: new AttributeRedactionPolicy() }); // very conservative key-oriented policy
await configureTelemetry(client, "dedicated", { redaction: false });                          // disabled - no redaction
await configureTelemetry(client, "dedicated", {                                               // custom callback to control how attributes get redacted
  redaction: (key, value) => (key.includes("email") ? undefined : value),
});
PolicyStrategyTrade-off
RegexRedactionPolicy (default, redaction: true)Content-oriented: keeps keys and structure, redacts matched substrings (secret tokens plus PII — emails, card-like sequences, IPv4).Redacts most sensitive data while preserving observability value; may miss free-form PII or secrets not in the pattern set.
AttributeRedactionPolicyKey-oriented: redacts whole values for sensitive keys (explicit set, fragment match, or non-primitive value), then scans kept values for secret token patterns.Very conservative, but erases most prompt/response content.
CallbackRedactionPolicy (redaction: <callback>)Your (key, value) => value | undefined masker per attribute; return undefined to drop the attribute.Full control; you own the logic.

The built-in defaults are exported as constants, so you can extend them instead of replacing them wholesale:

import {
  AttributeRedactionPolicy,
  DEFAULT_PII_SECRET_PATTERNS,
  DEFAULT_SENSITIVE_ATTRIBUTE_KEYS,
  RegexRedactionPolicy,
  configureTelemetry,
} from "@mistralai/mistralai/extra/observability";

// Content-oriented: add a custom secret pattern to the default set.
await configureTelemetry(client, "dedicated", {
  redaction: new RegexRedactionPolicy([...DEFAULT_PII_SECRET_PATTERNS, /\bacme-[a-z0-9]{16}\b/g]),
});

// Key-oriented: mask an extra application attribute on top of the defaults.
await configureTelemetry(client, "dedicated", {
  redaction: new AttributeRedactionPolicy({
    sensitiveKeys: new Set([...DEFAULT_SENSITIVE_ATTRIBUTE_KEYS, "app.customer.email"]),
  }),
});

Note: the RedactingSpanExporter primitive is reusable by any OpenTelemetry application, independent of the Mistral client.

Environment variables

VariableDescriptionDefault
MISTRAL_SDK_TELEMETRYAuto-enable telemetry: dedicated, global, or false.unset (disabled)
MISTRAL_OTLP_TRACES_ENDPOINTOverride the OTLP traces endpoint used in dedicated mode.https://api.mistral.ai/telemetry/v1/traces
MISTRAL_API_KEYUsed as the bearer token for the dedicated-mode exporter.—

Runnable examples live in examples/src/observability.

Development

Contributions

While we value open-source contributions to this SDK, this library is generated programmatically. Any manual changes added to internal files will be overwritten on the next generation. We look forward to hearing your feedback. Feel free to open a PR or an issue with a proof of concept and we'll do our best to include it in a future release.

Project health

npm

@mistralai/mistralai

Latest release

2.7.0 · Sep 9, 2026

Releases this year

23

Significant stargazers

Arnaud Benhamdine

56 followers · starred Mar 2025

Murtuzaali Surti

171 followers · starred Dec 2024

Martin Oppitz

51 followers · starred Mar 2026

Otto Sulin

89 followers · starred Jan 2026

Similar repos

mistralai/client-python

Python client library for Mistral AI platform

773

same org

mistralai/mistral-vibe

Minimal CLI coding agent by Mistral

5,105

same org

mistralai/cookbook

2,341

same org

openai/openai-node

Official JavaScript / TypeScript library for the OpenAI API

11,217

meta-llama/llama-api-typescript

The official Typescript library for the Llama API

38

groq/groq-typescript

The official Node.js / Typescript library for the Groq API

266

codeany-ai/open-agent-sdk-typescript

Agent-SDK without CLI dependencies, as an alternative to claude-agent-sdk, completely open source

2,745

googleapis/js-genai

TypeScript/JavaScript SDK for Gemini and Vertex AI.

1,690