Mistral Nemo chat

openrouter
mistral
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, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.

Capabilities

Context Window 131k tokens
Max Output 16k tokens
Inputs
Outputs

Pricing (per 1M tokens)

Input $0.02
Output $0.04
Cache Read -
Cache Write -

Supported Parameters

frequency_penaltymax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p