Mistral: Mistral Nemo
mistralai
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,...
- Context window
- 131,072 tokens
- Input cost
- $0.02 / 1M
- Output cost
- $0.04 / 1M
- Latency (p50)
- —