Loading...
Loading...
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,...
Input
$0.02
per 1M tokens
Output
$0.03
per 1M tokens
Blended
$0.02
per 1M tokens
Cheaper than 92% of models. Median price is $0.56/1M tokens.
Daily
$0.02
Monthly
$0.67
Context Window
131K
tokens
Larger than 33% of models
Max Output
16K
tokens
13% of context
Context Window Comparison
Price/1M
$0.02
51st cheapest
96% below median
Top 8%
Context Window
131K
201st largest
Top 67%