← Back to Directory

Mistral: Mistral Nemo

MISTRALAI Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1042Aider: 22.6%
Max Context Limit131,072Max Out: 16,384 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1M$0.05Blended Standard Rate

Model Capabilities & Contract SLAs

  • Agentic
  • 📋 Strict JSON Schema
  • 🛠️ Native Tool Calling
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.02 / 1M
Output Tokens (Completion)$0.03 / 1M

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

Evaluate Competitors

VS Engine MatchupMistral: Mistral Nemo vs Inference.net: Schematron V2 SmallVS Engine MatchupMistral: Mistral Nemo vs Qwen: Qwen2.5 7B InstructVS Engine MatchupMistral: Mistral Nemo vs Body Builder (beta)VS Engine MatchupMistral: Mistral Nemo vs Xiaomi: MiMo-V2.5VS Engine MatchupMistral: Mistral Nemo vs OpenAI: gpt-oss-20b (batch)VS Engine MatchupMistral: Mistral Nemo vs Microsoft: Phi 4