mistralai/mistral-nemo
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,...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| DekaLLMfp8 | $0.020 | $0.030 | 131K | 92.8% |
| DeepInfrafp8 | $0.020 | $0.040 | 131K | 99.8% |
| Novitafp8 | $0.040 | $0.170 | 60K | 74.2% |
| Mistral | $0.150 | $0.150 | 131K | 99.9% |
Mistral Nemo costs $0.020 per million input tokens and $0.030 per million output tokens via OpenRouter, making it 4th cheapest of 298 paid models.
Mistral Nemo generates around 77 tokens per second with 273ms time-to-first-token (p50), the 98th fastest tracked model.
Mistral Nemo supports a 131K-token context window. It accepts text input.