token.app › Mistral AI › Mistral Nemo
Mistral Nemo pricing & benchmarks
Mistral Nemo is available from Mistral AI at $0.019 per million input tokens and $0.030 per million output tokens ($0.022 blended at 3:1). It accepts up to 131,072 tokens of context. 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,...
Pricing
Per million tokens · OpenRouter
Input$0.019
Output$0.030
Blended (3:1)$0.022
Specification
mistralai/mistral-nemo
Context window131K
Max output16K
ReleasedJul 2024
LicenceOpen weights
Modalitiesin:text, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 29.9% ±2.1 | — | 2025-01-27 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Where to run Mistral Nemo
4 hosts · 3.3× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| DeepInfra | $0.022 | $0.019 / $0.030 | 131K | fp8 | 97.9% |
| Parasail | $0.030 | $0.030 / $0.030 | 131K | fp8 | 99.8% |
| Io Net | $0.072 | $0.042 / $0.160 | 128K | fp16 | 97.8% |
| Novita ⚠ 60K context, not 131K |
$0.072 | $0.040 / $0.170 | 60K | fp8 | 68.6% |
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Mistral Nemo
FAQ
How much does Mistral Nemo cost?
Mistral Nemo costs $0.019 per million input tokens and $0.030 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.022 per million tokens.
What is Mistral Nemo's context window?
Mistral Nemo accepts up to 131,072 tokens of context, and can generate up to 16,384 output tokens.
How good is Mistral Nemo on benchmarks?
Mistral Nemo scores 29.9% on GPQA Diamond, independently run and published by Epoch AI. 1 benchmark result are listed on this page, each with its run date and source.