← All models
M
Mistral: Mistral Nemo
mistralai/mistral-nemo
Tool useJSONStreaming
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,...
Pricing
Input
$0.02 / 1M
Output
$0.03 / 1M
Specs
Context
131,072 tokens
Input
text
Output
text
Knowledge cutoff: 2024-04-30
Released: 2024-07
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p