AI model · Mistral
Mistral Nemo
Model ID: mistralai/mistral-nemo
- Input
- $0.02 per 1M tokens
- Output
- $0.03 per 1M tokens
- Context
- 131K tokens at once
- Max output
- 16K tokens per reply
- Released
- 19 Jul 2024 Mistral
What it can do
- NoReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
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,...
Sources
- Mistral: Mistral Nemo on OpenRouter — read 2 Oct 2026