About
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,...
Related Models
Pricing
Input
$0.02
per 1M tokens
Output
$0.03
per 1M tokens
Blended
$0.02
per 1M tokens
Cheaper than 91% of models. Median price is $0.54/1M tokens.
Cost Calculator
Tokens per day1M
100K100M
Daily
$0.02
Monthly
$0.67
vs. Similar Models
Llama 3.1 8B
$0.020%
Qwen3.5 0.8B
$0.02-11%
Qwen3.5 0.8B (Non-reasoning)
$0.02-11%
Gemma 3n E4B Instruct
$0.03+11%
Performance
Context Window
131K
tokens
Larger than 27% of models
Max Output
16K
tokens
13% of context
Context Window Comparison
DeepSeek V3.2
131KSame
gpt oss 120b
131KSame
MoonshotAI: Kimi K2 0711
131KSame