Mistral Nemo 12B
By mistral
mistral/mistral-nemoA 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.
ReleasedJul 18, 2024
Pricing
Pricing (Input)$0.04/M
Pricing (Output)$0.17/M
CachingNo
Limits
Context Length60.3K
Max Output Tokens16K
Input Modalities
TextSupported
ImageNot supported
PDFNot supported
AudioNot supported
Output Modalities
TextSupported
ImageNot supported
AudioNot supported
Features
ReasoningNot supported
ToolsSupported
TemperatureSupported