mistral-rate-limits

name	mistral-rate-limits
description	Implement Mistral AI rate limiting, backoff, and request management. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Mistral AI. Trigger with phrases like "mistral rate limit", "mistral throttling", "mistral 429", "mistral retry", "mistral backoff".
allowed-tools	Read, Write, Edit
version	1.12.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","mistral","api"]
compatibility	Designed for Claude Code, also compatible with Codex and OpenClaw

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.

Endpoint	What's limited
/v1/chat/completions	RPM + TPM (input + output)
/v1/embeddings	RPM + TPM (input only)
/v1/fim/completions	RPM + TPM
/v1/moderations	RPM

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;
    : ;

  () {
    . = rpm;
    . = tpm;
  }

   (: ): <> {
     now = .();
     windowStart = now - ;

    
    . = ..( t > windowStart);
    . = ..( b. > windowStart);

    
     (.. >= .) {
       waitMs = .[] - windowStart + ;
      .();
        ( (r, waitMs));
    }

    
     currentTPM = ..( sum + b., );
     (currentTPM + estimatedTokens > .) {
       waitMs = .[]. - windowStart + ;
      .();
        ( (r, waitMs));
    }

    ..(.());
  }

  (: ):  {
    ..({ : .(), tokens });
  }
}