Mistral: Ministral 3 14B 2512

MISTRALAI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗

Intelligence (ELO)1419Chatbot Arena Verified

Max Context Limit262,144Max Out: 209,715 tokens

Prompt Caching90% OFF$0.02 / 1M cached

Standard API / 1M$0.40Blended Standard Rate

Model Capabilities & Contract SLAs

Drafting
Classification
Agentic
Coding & Logic
Fictional
📋 Strict JSON Schema
🛠️ Native Tool Calling

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and efficient language...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.20 / 1M

⚡ Cached Input (Prompt Cache Read)90% OFF$0.02 / 1M

Output Tokens (Completion)$0.20 / 1M

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

Evaluate Competitors

VS Engine MatchupMistral: Ministral 3 14B 2512 vs AionLabs: Aion 3.5 Mini VS Engine MatchupMistral: Ministral 3 14B 2512 vs DeepSeek: DeepSeek V4 Flash Vision Exp VS Engine MatchupMistral: Ministral 3 14B 2512 vs AionLabs: Aion-3.0-Mini VS Engine MatchupMistral: Ministral 3 14B 2512 vs NVIDIA: Nemotron 3 Ultra VS Engine MatchupMistral: Ministral 3 14B 2512 vs SpaceXAI: Grok 4.20 VS Engine MatchupMistral: Ministral 3 14B 2512 vs Anthropic: Claude Haiku 4.5