← Back to Directory

Mistral: Ministral 3 3B 2512

MISTRALAI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1425Chatbot Arena Verified
Max Context Limit131,072Max Out: 104,857 tokens
Prompt Caching90% OFF$0.01 / 1M cached
Standard API / 1M$0.20Blended Standard Rate

Model Capabilities & Contract SLAs

  • Drafting
  • Classification
  • Vision
  • Agentic
  • Coding & Logic
  • Fictional
  • 📋 Strict JSON Schema
  • 🛠️ Native Tool Calling
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.10 / 1M
⚡ Cached Input (Prompt Cache Read)90% OFF$0.01 / 1M
Output Tokens (Completion)$0.10 / 1M

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

Evaluate Competitors

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