Mistral AI rolled out a major update to Codestral 2501, expanding native context length to 256K tokens. The model achieves over 98% accuracy on 200k Fill-in-the-Middle (FIM) benchmarks, with broad multilingual fluency spanning 80+ mainstream and emerging languages including Rust, Go, Python, Solidity, and Zig.

Key Takeaways

  • ✓Context window expanded to 256K tokens for repo-scale file comprehension.
  • ✓Achieves 98%+ FIM accuracy across long 200k spans with strict syntax adherence.
  • ✓Available immediately via La Plateforme API and the Mistral Vibe CLI.
⚡

Key Decision Metrics at a Glance

TL;DR Verdict
🏆 Benchmark RankRank
Achieves 98%+ FIM accuracy across long 200k spans with strict syntax adherence.
Full Leaderboard→
💰 Cost & PlansCompare
API & Subscription
Compare Plans↗
🛠️ Ecosystem & IDERules
mistral · codestral · fim
Setup IDE Rules↗
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗
Up NextMistral AI Upgrades Codestral 2501 & Large 3: 256K Context Window with Accelerated FIM Completion
Read Now→