Mistral Nemo
Mistral · Open weights · Released Jul 19, 2024 · mistralai/mistral-nemo
131K contextToolsStructured outputPrompt cachingOpen weights
Available from 4 providersUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.019 | $0.03 | — | 131K | fp8 | ✕ | ✕ | 96.3% | |
| $0.03 | $0.03 | — | 131K | fp8 | ✕ | ✕ | 99.9% | |
| $0.04 | $0.17 | — | 60K | fp8 | 3.6s | 33 tok/s | 60.3% | |
| INIo Net | $0.044 | $0.16 | $0.029 | 128K | fp16 | 2.5s | 60 tok/s | 96.0% |
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 43 hours ago
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,...
Specifications
Context window131,072
Max output16,384
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedJul 19, 2024
Knowledge cutoff2024-04-30
TokenizerMistral
WeightsHugging Face ↗
Open weights
safetensors
Related
Embed badge
[](https://modelindex.ai/models/mistralai/mistral-nemo)Sources
OpenRouter API4 minutes ago
AGGREGATORHugging Face4 minutes ago
COMMUNITYModelIndex benchmarks43 hours ago
MEASUREDVerified 4 minutes ago · list prices, not negotiated rates.