← Back to Directory

Mistral: Codestral 2508

MISTRALAI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1425Chatbot Arena Verified
Max Context Limit256,000Max Out: 204,800 tokens
Prompt Caching90% OFF$0.03 / 1M cached
Standard API / 1M$1.20Blended Standard Rate

Model Capabilities & Contract SLAs

  • Agentic
  • Coding & Logic
  • Fictional
  • 📋 Strict JSON Schema
  • 🛠️ Native Tool Calling
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.30 / 1M
⚡ Cached Input (Prompt Cache Read)90% OFF$0.03 / 1M
Output Tokens (Completion)$0.90 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupMistral: Codestral 2508 vs Z.ai: GLM Flash LatestVS Engine MatchupMistral: Codestral 2508 vs Mistral: Ministral 3 3B 2512VS Engine MatchupMistral: Codestral 2508 vs Qwen: Qwen3 VL 8B ThinkingVS Engine MatchupMistral: Codestral 2508 vs DeepSeek: DeepSeek V3.2 ExpVS Engine MatchupMistral: Codestral 2508 vs Qwen: Qwen3 235B A22B Thinking 2507VS Engine MatchupMistral: Codestral 2508 vs Morph: Morph V3 Fast