Models/Mistral/Mistral Nemo

Mistral Nemo

Mistral · Open weights · Released Jul 19, 2024 · mistralai/mistral-nemo
Best $0.018 in / $0.03 out via DekaLLM · fp8
CompareEstimate cost
131K contextToolsStructured outputPrompt cachingOpen weights
Available from 6 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 5 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
PROVIDERINPUTOUTPUTCACHECONTEXTQUANTTTFTTPSUPTIME
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 5 minutes ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Recent changesRSS ↗
Sep 25, 2026endpoint added · io-net4 → 6
Sep 25, 2026endpoint added · mistral4 → 6
Sep 23, 2026endpoint removed · io-net5 → 4
Sep 12, 2026endpoint added · dekallm4 → 5
Aug 31, 2026endpoint removed · mistral5 → 4
Aug 24, 2026endpoint added · mistral4 → 5
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
Open weights
Downloads334.4K
Likes1.7K
Licenseapache-2.0
safetensors
Embed badge
Mistral Nemo price and speed badge
[![Mistral Nemo](https://modelindex.ai/badge/mistralai/mistral-nemo)](https://modelindex.ai/models/mistralai/mistral-nemo)
Sources
OpenRouter API23 minutes ago
AGGREGATOR
Hugging Face23 minutes ago
COMMUNITY
ModelIndex benchmarks8 days ago
MEASURED
Verified 23 minutes ago · list prices, not negotiated rates.