← model directory

mistralai

Mistral: Mistral Nemo

mistralai/mistral-nemo

↓ runs free on your own hardware

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,...

specs & pricing
Type
text
Provider
mistralai
Model ID
mistralai/mistral-nemo
Capabilities
tools
Context window
131K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.022 / 1M tokens
Output price
$0.033 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

Mistral: Mistral Nemo — pricing, context & specs | Wide Area Intelligence