Mistral
Mistral: Mistral Nemo
mistralai/mistral-nemoHugging Face ↗
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,...
Mistral: Mistral Nemo usage over time
OpenRouter share of tokens, by day.
Mistral: Mistral Nemo holds 0.23% today, down from 3.95% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
Mistral: Mistral Nemo's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-09-05, Mistral: Mistral Nemo holds 0.2% of OpenRouter token share, down 0.06pp over 30 days. Source: Tidelines (OpenRouter).
Cost per session
Median dollars spent on one Mistral: Mistral Nemo session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn |
|---|---|
| Hermes Agent | $0.0005 |
Where to run it
Mistral: Mistral Nemo pricing by provider
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
Mistral: Mistral Nemo is served by 4 tracked endpoints on OpenRouter. The cheapest output price is $0.03 per million tokens from DeepInfra, and the most expensive is $0.17 from Novita. The largest context window offered is 131k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| DeepInfra | $0.02 | $0.03 | 131k | 99.97% |
| Parasail | $0.03 | $0.03 | 131k | 99.80% |
| Io Net | $0.04 | $0.16 | 128k | 99.88% |
| Novita | $0.04 | $0.17 | 60k | 37.09% |