Mistral Nemo
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,...
The figures
- Made by
- Mistral
- Model ID
- mistralai/mistral-nemo
- Input
- $0.019 per million tokens
- Output
- $0.03 per million tokens
- Context window
- 131K tokens
- Longest answer
- 16K tokens
- Takes in
- text
- Gives back
- text
- Reasoning
- No
- Tool calling
- Yes
- Reads images
- No
- Open weights
- Yes
- Released
- 19 Jul 2024
Read on 3 Oct 2026.