Mistral: Devstral 2 2512
MISTRALAI Developer Architecture Profile
Intelligence (ELO)1442Chatbot Arena Verified
Max Context Limit262,144Max Out: 209,715 tokens
Prompt Caching90% OFF$0.04 / 1M cached
Standard API / 1M$2.40Blended Standard Rate
Model Capabilities & Contract SLAs
- Agentic
- Coding & Logic
- Fictional
- 📋 Strict JSON Schema
- 🛠️ Native Tool Calling
Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...
Granular Pricing Matrix
Input Tokens (Standard Prompt)$0.40 / 1M
⚡ Cached Input (Prompt Cache Read)90% OFF$0.04 / 1M
Output Tokens (Completion)$2.00 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupMistral: Devstral 2 2512 vs Apodex: Apodex 1.1 Mini (free)VS Engine MatchupMistral: Devstral 2 2512 vs Z.ai: GLM 5V TurboVS Engine MatchupMistral: Devstral 2 2512 vs ByteDance Seed: Seed-2.0-MiniVS Engine MatchupMistral: Devstral 2 2512 vs Qwen: Qwen3.5-122B-A10BVS Engine MatchupMistral: Devstral 2 2512 vs Relace: Relace SearchVS Engine MatchupMistral: Devstral 2 2512 vs TheDrummer: Skyfall 36B V2