Back to all models
mistralai
mistralaiMistral: 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,...
mistralai/mistral-nemo
Context Size
131.072K
Input Price
3,000 pts/M
Output Price
4,500 pts/M
Architecture
Text
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerMistral
Instruct Typemistral
Provider Context131.072K tokens
ModeratedNo
CreatedJul 19, 2024