Mistral Nemo

Mistral · mistralai/mistral-nemo

← Back to leaderboard

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,...

open weightstexttext->text

Context

Max context: 131072
Max output:

Pricing

Input / 1M: 0.02
Output / 1M: 0.03
Blend / 1M: 0.03

Quality

Quality index:

Provider

Provider: Mistral
Moderated: no