Mistral AI Install & Auth

Overview

Set up the official Mistral AI SDK (@mistralai/mistralai for TypeScript, mistralai for Python) and configure authentication for chat completions, embeddings, function calling, vision, and agents.

Prerequisites

• Node.js 18+ or Python 3.9+
• Package manager (npm, pnpm, yarn, or pip)
• Mistral AI account at console.mistral.ai
• API key from La Plateforme (Settings > API Keys)

Instructions

Step 1: Install SDK

Node.js (TypeScript/JavaScript) — ESM only

set -euo pipefail
# npm
npm install @mistralai/mistralai

# pnpm
pnpm add @mistralai/mistralai

# yarn
yarn add @mistralai/mistralai

Python

set -euo pipefail
pip install mistralai

Step 2: Configure Authentication

Environment Variables (Recommended)

# Set in shell
export MISTRAL_API_KEY="your-api-key"

# Or create .env file (add to .gitignore!)
echo 'MISTRAL_API_KEY=your-api-key' >> .env
echo '.env' >> .gitignore

Using dotenv (Node.js)

set -euo pipefail
npm install dotenv

import 'dotenv/config';

Step 3: Verify Connection

TypeScript

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

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

async function testConnection() {
  try {
    const models = await client.models.list();
    console.log('Connection successful! Available models:');
    for (const model of models.data ?? []) {
      console.log(`  - ${model.id}`);
    }
  } catch (error: any) {
    if (error.status === 401) {
      console.error('Invalid API key. Check your key at console.mistral.ai');
    } else {
      console.error('Connection failed:', error.message);
    }
  }
}

testConnection();

Python

import os
from mistralai import Mistral

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

def test_connection():
    try:
        models = client.models.list()
        print("Connection successful! Available models:")
        for model in models.data:
            print(f"  - {model.id}")
    except Exception as e:
        print(f"Connection failed: {e}")

test_connection()

Step 4: Production — Secret Manager

// GCP Secret Manager (recommended for production)
import { SecretManagerServiceClient } from '@google-cloud/secret-manager';

const sm = new Se

Mistral AI Local Dev Loop

Overview

Set up a fast, reproducible local development workflow for Mistral AI integrations: project scaffold, environment config, hot reload with tsx, unit tests with Vitest mocking, and integration tests against the live API.

Prerequisites

• Completed mistral-install-auth setup
• Node.js 18+ with npm/pnpm
• MISTRALAPIKEY set in environment

Instructions

Step 1: Project Structure

my-mistral-project/
├── src/
│   ├── mistral/
│   │   ├── client.ts       # Singleton client
│   │   ├── config.ts       # Config with Zod validation
│   │   └── types.ts        # TypeScript types
│   └── index.ts
├── tests/
│   ├── unit/
│   │   └── mistral.test.ts
│   └── integration/
│       └── mistral.integration.test.ts
├── .env.local              # Local secrets (git-ignored)
├── .env.example            # Template for team
├── tsconfig.json
├── vitest.config.ts
└── package.json

Step 2: Package Configuration

package.json

{
  "type": "module",
  "scripts": {
    "dev": "tsx watch src/index.ts",
    "build": "tsc",
    "test": "vitest run",
    "test:watch": "vitest",
    "test:integration": "vitest run tests/integration/",
    "typecheck": "tsc --noEmit"
  },
  "dependencies": {
    "@mistralai/mistralai": "^1.0.0"
  },
  "devDependencies": {
    "@types/node": "^20.0.0",
    "dotenv": "^16.0.0",
    "tsx": "^4.0.0",
    "typescript": "^5.0.0",
    "vitest": "^1.0.0"
  }
}

tsconfig.json

{
  "compilerOptions": {
    "target": "ES2022",
    "module": "NodeNext",
    "moduleResolution": "NodeNext",
    "strict": true,
    "esModuleInterop": true,
    "skipLibCheck": true,
    "outDir": "dist",
    "rootDir": "src"
  },
  "include": ["src/**/*"],
  "exclude": ["node_modules", "dist"]
}

Step 3: Environment Setup

# Create environment template
cat > .env.example << 'EOF'
MISTRAL_API_KEY=your-api-key-here
MISTRAL_MODEL=mistral-small-latest
LOG_LEVEL=debug
EOF

cp .env.example .env.local
echo '.env.local' >> .gitignore
echo '.env' >> .gitignore

Step 4: Client Module

// src/mistral/client.ts
import { Mistral } from '@mistralai/mistralai';

Mistral AI Migration Deep Dive

Current State

!npm list openai @anthropic-ai/sdk @mistralai/mistralai 2>/dev/null | grep -E "openai|anthropic|mistral" || echo 'No AI SDKs found'

Overview

Comprehensive migration guide from OpenAI or Anthropic to Mistral AI using the adapter pattern with feature-flag controlled rollout. Covers model mapping, API differences, prompt adjustments, validation testing, and rollback procedures.

Prerequisites

• Current AI integration documented
• Mistral AI SDK installed (@mistralai/mistralai)
• Feature flag infrastructure (env vars or LaunchDarkly)
• Rollback plan tested

Migration Complexity

Instructions

Step 1: Assessment — Find All AI Touchpoints

set -euo pipefail
# Count integration points
echo "=== AI Integration Assessment ==="
echo "OpenAI imports: $(grep -r "from 'openai'" src/ --include='*.ts' -l 2>/dev/null | wc -l)"
echo "Anthropic imports: $(grep -r "from '@anthropic'" src/ --include='*.ts' -l 2>/dev/null | wc -l)"
echo "Chat completions: $(grep -r "chat\.completions\|messages\.create" src/ --include='*.ts' -c 2>/dev/null | wc -l)"
echo "Embeddings: $(grep -r "embeddings\.create" src/ --include='*.ts' -c 2>/dev/null | wc -l)"
echo "Streaming: $(grep -r "stream\|for await" src/ --include='*.ts' -c 2>/dev/null | wc -l)"

Step 2: Model Mapping

Step 3:

Mistral AI Observability

Overview

Monitor Mistral AI API usage, latency, token consumption, error rates, and costs. Covers instrumented client wrapper, Prometheus metrics, Grafana dashboard panels, alerting rules, and structured logging.

Prerequisites

• Mistral API integration in production
• Prometheus or OpenTelemetry-compatible metrics backend
• Alerting system (Alertmanager, PagerDuty, or similar)

Instructions

Step 1: Instrumented Client Wrapper

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

const PRICING: Record<string, { input: number; output: number }> = {
  'mistral-small-latest':  { input: 0.10, output: 0.30 },
  'mistral-large-latest':  { input: 0.50, output: 1.50 },
  'codestral-latest':      { input: 0.30, output: 0.90 },
  'mistral-embed':         { input: 0.10, output: 0 },
};

interface MetricsEvent {
  model: string;
  endpoint: string;
  durationMs: number;
  status: 'success' | 'error';
  statusCode?: number;
  inputTokens?: number;
  outputTokens?: number;
  costUsd?: number;
}

function emitMetrics(event: MetricsEvent): void {
  // Push to your metrics backend (Prometheus, Datadog, etc.)
  console.log(JSON.stringify({ type: 'mistral_metric', ...event }));
}

async function instrumentedChat(
  client: Mistral,
  model: string,
  messages: any[],
  options?: any,
) {
  const start = performance.now();
  try {
    const response = await client.chat.complete({ model, messages, ...options });
    const duration = Math.round(performance.now() - start);
    const pricing = PRICING[model] ?? PRICING['mistral-small-latest'];
    const pt = response.usage?.promptTokens ?? 0;
    const ct = response.usage?.completionTokens ?? 0;

    emitMetrics({
      model,
      endpoint: 'chat.complete',
      durationMs: duration,
      status: 'success',
      inputTokens: pt,
      outputTokens: ct,
      costUsd: (pt / 1e6) * pricing.input + (ct / 1e6) * pricing.output,
    });

    return response;
  } catch (error: any) {
    emitMetrics({
      model,
      endpoint: 'chat.complete',
      durationMs: Math.round(performance.now() - start),
      status: 'error',
      statusCode: error.status,
    });
    throw error;
  }
}

Step 2: Prometheus Metrics

// Using prom-client
import { Counter, Histogram, Gauge } from 'prom-client';

const mistralRequests = new Counter({
  name: 'mistral_requests_total',
  help: 'Total Mistral API requests',
  labelNames: ['model', 'endpoint', 'status'],
});

const mistralDuration = new Histogram({
  name: 'mistral_request_duration_ms',
  help: 'Mistral request duration in milliseconds',
  labelNames: ['model', 'endpoint'],
  buckets: [100, 250, 500, 10

Mistral AI Performance Tuning

Overview

Optimize Mistral AI API response times and throughput. Key levers: model selection (Mistral Small ~200ms TTFT vs Large ~500ms), prompt length (fewer tokens = faster), streaming (perceived speed), caching (zero-latency repeats), and concurrent request management.

Prerequisites

• Mistral API integration in production
• Understanding of RPM/TPM limits for your tier
• Application architecture supporting streaming

Instructions

Step 1: Model Selection by Latency Budget

const MODELS_BY_USE_CASE: Record<string, { model: string; ttftMs: string; note: string }> = {
  realtime_chat:     { model: 'mistral-small-latest',  ttftMs: '~200ms',  note: '256k ctx, cheapest' },
  code_completion:   { model: 'codestral-latest',      ttftMs: '~150ms',  note: 'Optimized for code + FIM' },
  code_agents:       { model: 'devstral-latest',       ttftMs: '~300ms',  note: 'Agentic coding tasks' },
  reasoning:         { model: 'mistral-large-latest',  ttftMs: '~500ms',  note: '256k ctx, strongest' },
  vision:            { model: 'pixtral-large-latest',  ttftMs: '~600ms',  note: 'Image + text multimodal' },
  embeddings:        { model: 'mistral-embed',         ttftMs: '~50ms',   note: '1024-dim, batch-friendly' },
  edge_devices:      { model: 'ministral-latest',      ttftMs: '~100ms',  note: '3B-14B, fastest' },
};

Step 2: Streaming for User-Facing Responses

Streaming reduces perceived latency from 1-2s (full response) to ~200ms (first token):

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

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

async function* streamChat(messages: any[], model = 'mistral-small-latest') {
  const stream = await client.chat.stream({ model, messages });
  for await (const chunk of stream) {
    const content = chunk.data?.choices?.[0]?.delta?.content;
    if (content) yield content;
  }
}

// Web Response with SSE
function streamToSSE(messages: any[]): Response {
  const encoder = new TextEncoder();
  const readable = new ReadableStream({
    async start(controller) {
      for await (const text of streamChat(messages)) {
        controller.enqueue(encoder.encode(`data: ${JSON.stringify({ text })}\n\n`));
      }
      controller.enqueue(encoder.encode('data: [DONE]\n\n'));
      controller.close();
    },
  });
  return new Response(readable, {
    headers: { 'Content-Type': 'text/event-stream', 'Cache-Control': 'no-cache' },
  });
}

Step 3: Response Caching

import { createHash } from 'crypto';
import { LRUCache } fr

Mistral AI Production Checklist

Overview

Complete checklist for deploying Mistral AI integrations to production. Covers credential management, code quality gates, health endpoints, circuit breaker resilience, gradual rollout, and rollback procedures.

Prerequisites

• Staging environment tested and verified
• Production API keys from La Plateforme
• Deployment pipeline (CI/CD) configured
• Monitoring and alerting ready (see mistral-observability)

Instructions

Step 1: Pre-Deployment Verification

Credentials

• [ ] Production API key stored in secret manager (never in env files or code)
• [ ] Key tested with curl -H "Authorization: Bearer $KEY" https://api.mistral.ai/v1/models
• [ ] Key has appropriate model access scope
• [ ] Fallback key available for rotation

Code Quality

• [ ] npm run typecheck passes
• [ ] npm test passes (unit + integration)
• [ ] No hardcoded keys: grep -r "MISTRALAPIKEY\|sk-" src/ --include="*.ts"
• [ ] Error handling covers 401, 429, 500+ status codes
• [ ] Rate limiting/backoff implemented
• [ ] Logging excludes message content and API keys

Model Configuration

• [ ] Using versioned model IDs or -latest aliases intentionally
• [ ] maxTokens set to prevent runaway costs
• [ ] temperature set appropriately (0 for deterministic, 0.7 for creative)
• [ ] Token budget alerts configured

Step 2: Health Check Endpoint

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

interface HealthStatus {
  status: 'healthy' | 'degraded' | 'unhealthy';
  provider: 'mistral';
  latencyMs: number;
  model?: string;
  error?: string;
}

export async function checkHealth(): Promise<HealthStatus> {
  const start = performance.now();
  try {
    const client = new Mistral({ apiKey: process.env.MISTRAL_API_KEY! });
    const models = await client.models.list();
    const latencyMs = Math.round(performance.now() - start);

    return {
      status: latencyMs > 5000 ? 'degraded' : 'healthy',
      provider: 'mistral',
      latencyMs,
      model: models.data?.[0]?.id,
    };
  } catch (error: any) {
    return {
      status: 'unhealthy',
      provider: 'mistral',
      latencyMs: Math.round(performance.now() - start),
      error: error.message,
    };
  }
}

// Express route
app.get('/health', async (req, res) => {
  const health = await checkHealth();
  res.status(health.status === 'unhealthy' ? 503 : 200).json(health);
});

Step 3: Circuit Breaker

Mistral Rate Limits

Overview

Rate limit management for Mistral AI API. Mistral enforces per-workspace RPM (requests/minute) and TPM (tokens/minute) limits that vary by usage tier (Experiment free tier vs Scale pay-as-you-go). View your workspace limits at admin.mistral.ai/plateforme/limits.

Prerequisites

• Mistral API key configured
• Understanding of workspace tier (Experiment vs Scale)
• Application with retry infrastructure

Mistral Rate Limit Architecture

Limits are set at the workspace level, not per key. All API keys in a workspace share the same RPM/TPM budget.

Headers returned on every response:

• x-ratelimit-limit-requests — your RPM cap
• x-ratelimit-remaining-requests — remaining RPM
• x-ratelimit-limit-tokens — your TPM cap
• x-ratelimit-remaining-tokens — remaining TPM
• Retry-After — seconds to wait (on 429 only)

Instructions

Step 1: Token-Aware Rate Limiter

class MistralRateLimiter {
  private requestTimes: number[] = [];
  private tokenBuckets: Array<{ time: number; tokens: number }> = [];
  private readonly rpm: number;
  private readonly tpm: number;

  constructor(rpm: number, tpm: number) {
    this.rpm = rpm;
    this.tpm = tpm;
  }

  async waitIfNeeded(estimatedTokens: number): Promise<void> {
    const now = Date.now();
    const windowStart = now - 60_000;

    // Prune old entries
    this.requestTimes = this.requestTimes.filter(t => t > windowStart);
    this.tokenBuckets = this.tokenBuckets.filter(b => b.time > windowStart);

    // Check RPM
    if (this.requestTimes.length >= this.rpm) {
      const waitMs = this.requestTimes[0] - windowStart + 100;
      console.warn(`RPM limit (${this.rpm}), waiting ${waitMs}ms`);
      await new Promise(r => setTimeout(r, waitMs));
    }

    // Check TPM
    const currentTPM = this.tokenBuckets.reduce((sum, b) => sum + b.tokens, 0);
    if (currentTPM + estimatedTokens > this.tpm) {
      const waitMs = this.tokenBuckets[0].time - windowStart + 100;
      console.warn(`TPM limit (${this.tpm}), waiting ${waitMs}ms`);
      await new Promise(r => setTimeout(r, waitMs));
    }

    this.requestTimes.push(Date.now());
  }

  recordUsage(tokens: number): void {
    this.tokenBuckets.push({ time: Date.now(), tokens 

Mistral AI Reference Architecture

Overview

Production-ready architecture patterns for Mistral AI integrations: layered project structure, singleton client, Zod-validated config, custom error classes, service layer with caching, health checks, prompt templates, and model routing.

Prerequisites

• TypeScript/Node.js project (ESM)
• @mistralai/mistralai SDK
• zod for config validation
• Testing framework (Vitest)

Layer Architecture

API Layer (Routes, Controllers, Middleware)
    |
Service Layer (Business Logic, Orchestration)
    |
Mistral Layer (Client, Config, Errors, Prompts)
    |
Infrastructure Layer (Cache, Queue, Monitoring)

Instructions

Step 1: Directory Structure

src/
├── mistral/
│   ├── client.ts         # Singleton client factory
│   ├── config.ts         # Zod-validated config
│   ├── errors.ts         # Custom error classes
│   ├── types.ts          # Shared types
│   └── prompts.ts        # Prompt templates
├── services/
│   ├── chat.service.ts   # Chat with caching + retry
│   ├── embed.service.ts  # Embeddings + search
│   └── rag.service.ts    # RAG pipeline
├── api/
│   ├── chat.route.ts     # HTTP endpoints
│   └── health.route.ts   # Health check
└── config/
    ├── base.ts           # Shared config
    ├── development.ts    # Dev overrides
    └── production.ts     # Prod overrides

Step 2: Config with Zod Validation

// src/mistral/config.ts
import { z } from 'zod';

const MistralConfigSchema = z.object({
  apiKey: z.string().min(10, 'MISTRAL_API_KEY required'),
  defaultModel: z.string().default('mistral-small-latest'),
  timeoutMs: z.number().default(30_000),
  maxRetries: z.number().default(3),
  cache: z.object({
    enabled: z.boolean().default(true),
    ttlMs: z.number().default(3_600_000),
    maxSize: z.number().default(5000),
  }).default({}),
});

export type MistralConfig = z.infer<typeof MistralConfigSchema>;

export function loadConfig(): MistralConfig {
  return MistralConfigSchema.parse({
    apiKey: process.env.MISTRAL_API_KEY,
    defaultModel: process.env.MISTRAL_MODEL,
    timeoutMs: process.env.MISTRAL_TIMEOUT ? Number(process.env.MISTRAL_TIMEOUT) : undefined,
  });
}

Step 3: Singleton Client

// src/mistral/client.ts
import { Mistral } from '@mistralai/mistralai';
import { loadConfig, type MistralConfig } from './config.js';

let _client: Mistral | null = null;
let _config: MistralConfig | null = null;

export function getMistralClient(): Mistral {
  if (!_client) {
    _config = loadConfig();
    _client = new Mistral({
      apiKey: _config.apiKey,
      timeoutMs: _config.timeoutMs,
      maxRetries: _config.maxRetries,
    });
  }
  return _client;
}

export function getConfig(): Mistr

Mistral SDK Patterns

Overview

Production-ready patterns for the Mistral AI SDK. Covers singleton client, retry/backoff, structured output, streaming, function calling, batch embeddings, and async Python — all with proper error handling. SDK is ESM-only for TypeScript (@mistralai/mistralai), sync+async for Python (mistralai).

Prerequisites

• @mistralai/mistralai (TypeScript) or mistralai (Python) installed
• MISTRALAPIKEY environment variable set

Instructions

Step 1: Singleton Client with Configuration

TypeScript

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

let _client: Mistral | null = null;

export function getMistralClient(): Mistral {
  if (!_client) {
    const apiKey = process.env.MISTRAL_API_KEY;
    if (!apiKey) throw new Error('MISTRAL_API_KEY not set');

    _client = new Mistral({
      apiKey,
      timeoutMs: 30_000,
      maxRetries: 3,
    });
  }
  return _client;
}

// Reset for testing
export function resetClient(): void {
  _client = null;
}

Python

import os
from mistralai import Mistral

_client = None

def get_client() -> Mistral:
    global _client
    if _client is None:
        api_key = os.environ.get("MISTRAL_API_KEY")
        if not api_key:
            raise RuntimeError("MISTRAL_API_KEY not set")
        _client = Mistral(api_key=api_key, timeout_ms=30_000, max_retries=3)
    return _client

Step 2: Structured Output with JSON Schema

import { z } from 'zod';

// Define schema with Zod, then convert to JSON Schema for Mistral
const TicketSchema = z.object({
  category: z.enum(['bug', 'feature', 'question']),
  severity: z.enum(['low', 'medium', 'high', 'critical']),
  summary: z.string(),
});

type Ticket = z.infer<typeof TicketSchema>;

async function classifyTicket(text: string): Promise<Ticket> {
  const client = getMistralClient();

  const response = await client.chat.complete({
    model: 'mistral-small-latest',
    messages: [
      { role: 'system', content: 'Classify the support ticket.' },
      { role: 'user', content: text },
    ],
    responseFormat: {
      type: 'json_schema',
      jsonSchema: {
        name: 'ticket_classification',
        schema: {
          type: 'object',
          properties: {
            category: { type: 'string', enum: ['bug', 'feature', 'question'] },
            severity: { type: 'string', enum: ['low', 'medium', 'high', 'critical'] },
            summary: { type: 'string' },
          },
      

Mistral Security Basics

Overview

Security practices for Mistral AI integrations: API key management, prompt injection defense, output sanitization, content moderation with mistral-moderation-latest, request logging without secrets, and key rotation.

Prerequisites

• Mistral API key provisioned
• Understanding of OWASP LLM Top 10 risks
• Secret management infrastructure

Instructions

Step 1: API Key Management

import os

# NEVER: api_key = "sk-abc123"

# Development — env vars
api_key = os.environ.get("MISTRAL_API_KEY")
if not api_key:
    raise RuntimeError("MISTRAL_API_KEY not set")

# Production — secret manager
from google.cloud import secretmanager

def get_api_key() -> str:
    client = secretmanager.SecretManagerServiceClient()
    response = client.access_secret_version(
        name="projects/my-project/secrets/mistral-api-key/versions/latest"
    )
    return response.payload.data.decode("UTF-8")

Step 2: Prompt Injection Defense

function sanitizeUserInput(input: string): string {
  // Strip common injection patterns
  const patterns = [
    /ignore (?:previous|all|above) instructions/gi,
    /you are now/gi,
    /system prompt/gi,
    /\boverride\b/gi,
    /\bforget\b.*\binstructions\b/gi,
  ];

  let sanitized = input;
  for (const pattern of patterns) {
    sanitized = sanitized.replace(pattern, '[FILTERED]');
  }

  // Limit length to prevent context stuffing
  return sanitized.slice(0, 4000);
}

function buildSafeMessages(system: string, userInput: string) {
  return [
    { role: 'system', content: system },
    {
      role: 'user',
      content: `<user_query>\n${sanitizeUserInput(userInput)}\n</user_query>`,
    },
  ];
}

Step 3: Content Moderation with Mistral API

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

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

async function moderateContent(text: string): Promise<{ safe: boolean; flags: string[] }> {
  const result = await client.classifiers.moderate({
    model: 'mistral-moderation-latest',
    inputs: [text],
  });

  const categories = result.results[0].categories;
  const flags = Object.entries(categories)
    .filter(([, flagged]) => flagged)
    .map(([category]) => category);

  return { safe: flags.length === 0, flags };
}

// Gate user input before processing
async function safeChatFlow(userInput: string) {
  const inputCheck = await moderateContent(userInput);
  if (!inputCheck.safe) {
    throw new Error(`Input flagged: ${inputCheck.flags.join(', ')}`);
  }

  const response = await client.chat.complete({
    model: 'mistral-small-latest',
    messages: [{ role: 'user', c

Mistral AI Upgrade & Migration

Current State

!npm list @mistralai/mistralai 2>/dev/null || echo 'not installed'

!pip show mistralai 2>/dev/null | grep -E "^(Name|Version)" || echo 'not installed'

Overview

Guide for upgrading the Mistral AI SDK between major versions. The TypeScript SDK (@mistralai/mistralai) moved from CommonJS to ESM-only in v1.x, with significant API surface changes. This skill covers version detection, breaking change migration, automated code transforms, and rollback.

Prerequisites

• Current Mistral AI SDK installed
• Git for version control
• Test suite available

Instructions

Step 1: Check Versions

set -euo pipefail
# Current version
npm list @mistralai/mistralai 2>/dev/null

# Latest available
npm view @mistralai/mistralai version

# All versions
npm view @mistralai/mistralai versions --json | jq '.[-5:]'

# Python
pip show mistralai 2>/dev/null | grep Version

Step 2: Known Breaking Changes (v0.x to v1.x)

Step 3: Automated Migration Script

// scripts/migrate-mistral-v1.ts
import { readFileSync, writeFileSync } from 'fs';
import { glob } from 'glob';

const TRANSFORMS = [
  // Import statement
  {
    find: /import\s+MistralClient\s+from\s+['"]@mistralai\/mistralai['"]/g,
    replace: "import { Mistral } from '@mistralai/mistralai'",
  },
  // Constructor
  {
    find: /new\s+MistralClient\((\w+)\)/g,
    replace: 'new Mistral({ apiKey: $1 })',
  },
  // Chat method (careful: only top-level .chat(), not .chat.complete())
  {
    find

Mistral AI Events, Agents & Async Patterns

Overview

Async and event-driven patterns for Mistral AI: the Agents API for stateful multi-turn workflows, Batch API for cost-effective bulk inference (50% cheaper), SSE streaming endpoints, background job queues, and Python async processing. Mistral does not have native webhooks — this skill covers the patterns that replace them.

Prerequisites

• @mistralai/mistralai SDK installed
• MISTRALAPIKEY configured
• For agents: La Plateforme access to create agents
• For batch: JSONL file preparation

Instructions

Step 1: Mistral Agents API

Create stateful agents with instructions, tools, and model configuration:

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

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

// Create an agent on La Plateforme
const agent = await client.agents.create({
  name: 'Code Reviewer',
  model: 'mistral-large-latest',
  instructions: `You are an expert code reviewer. Analyze code for:
    - Security vulnerabilities
    - Performance issues
    - Best practice violations
    Provide actionable feedback with severity ratings.`,
  description: 'Reviews code for security, performance, and best practices',
  tools: [
    {
      type: 'function',
      function: {
        name: 'search_codebase',
        description: 'Search the codebase for patterns',
        parameters: {
          type: 'object',
          properties: { query: { type: 'string' } },
          required: ['query'],
        },
      },
    },
  ],
});

// Chat with the agent (stateful conversation)
const response = await client.agents.complete({
  agentId: agent.id,
  messages: [
    { role: 'user', content: 'Review this function:\n```\nfunction auth(pwd) { return pwd === "admin123"; }\n```' },
  ],
});

console.log(response.choices?.[0]?.message?.content);

Step 2: Batch API for Bulk Inference

50% cost reduction for non-time-sensitive workloads:

// 1. Prepare JSONL input file
const batchRequests = [
  {
    custom_id: 'req-1',
    body: {
      model: 'mistral-small-latest',
      messages: [{ role: 'user', content: 'Summarize: ...' }],
      max_tokens: 200,
    },
  },
  {
    custom_id: 'req-2',
    body: {
      model: 'mistral-small-latest',
      messages: [{ role: 'user', content: 'Classify: ...' }],
      max_tokens: 50,
    },
  },
];

// Write to JSONL
import { writeFileSync } from 'fs';
writeFileSync('batch-input.jsonl',
  batchRequests.map(r => JSON.stringify(r)).join('\n')
);

// 2. Upload file and create batch job
const file = await client.files.upload({
  file: { fileN