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,...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.000000029 | $0.029 |
| completion | 0.00000003 | $0.030 |
{
"temperature": 0.3
}