Mistralai
Mistral: 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,...
| Specifications | |
|---|---|
| Provider | Mistralai |
| Input pricing | $0.02/M tokens |
| Output pricing | $0.03/M tokens |
| Context length | 131K tokens |
| Max output | 16K tokens |
| Input modalities | text |
| Output modalities | text |
| Tokenizer | Mistral |
| Knowledge cutoff | 2024-04-30 |
| Content moderated | No |
| HuggingFace | mistralai/Mistral-Nemo-Instruct-2407 |
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p