MMistral · Released Jul 19, 2024
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,...
- Released
- Jul 19 2024
- Context window
- 131K 16K out
- Input / 1M tokens
- $0.029 from $0.017
- Output / 1M tokens
- $0.03 from $0.022
Where to run it
18 providers compared
Cheapest: Io Net at $0.017 / $0.022 per 1M input / output tokens — 100% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Io NetFP16 | $0.017 | $0.022 | $0.011 | 128K | 102K | 99.9%24h | Cheapest |
| DekaLLMFP8 · no tool calling | $0.018 | $0.03 | — | 131K | 105K | 99.9%24h | +15% |
| Pioneer | $0.02 | $0.03 | $0.02 | 128K | 128K | — | +23% |
| Meganova | $0.02 | $0.04 | — | 131K | 66K | — | +37% |
| DeepInfraFP8 | $0.029 | $0.03 | — | 131K | 16K | 100%24h | +60% |
| Vercel AI Gateway | $0.029 | $0.03 | — | 131K | 131K | — | +60% |
| ParasailFP8 · no tool calling | $0.03 | $0.03 | — | 131K | 105K | 100%24h | +64% |
| Chutesno tool calling | $0.025 | $0.098 | $0.002 | 131K | 131K | — | +137% |
| Inference | $0.038 | $0.10 | — | 16K | 4K | — | +193% |
| NanoGPTno tool calling | $0.10 | $0.12 | $0.05 | 16K | 8K | — | +477% |
| OVHcloud AI Endpoints | $0.14 | $0.14 | — | 66K | 66K | — | +667% |
| Cortecs | $0.14 | $0.14 | $0.014 | 128K | 128K | — | +695% |
| Mistraleu | $0.15 | $0.15 | $0.015 | 131K | 105K | 98.9%24h | +722% |
| Kilo Gateway | $0.15 | $0.15 | $0.015 | 131K | 16K | — | +722% |
| Prime Inference | $0.17 | $0.17 | — | 131K | 16K | — | +811% |
| AI/ML API | $0.21 | $0.23 | $0.21 | 128K | 16K | — | +1067% |
| DigitalOcean | $0.30 | $0.30 | — | 128K | 16K | — | +1544% |
| Heliconeno tool calling | $20.00 | $40.00 | — | 128K | 16K | — | +136886% |
Benchmarks
Benchmark scores
No benchmark scores yet — Epoch AI hasn't evaluated Mistral Nemo. Scores appear here automatically once it does.
Specs
Details
- Model ID
mistralai/mistral-nemo- Developer
- Mistral
- Release date
- Jul 19, 2024 ·
- Context window
- 131,072 tokens
- Max output
- 16,384 tokens
- API price
- $0.029 / $0.03 per 1M input / output tokens
- Providers
- 18
- Input types
- text
- Reasoning
- No
- Tool calling
- Yes
- Open weights
- Yes
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.