Mistral Nemo
Joint Mistral/NVIDIA 12B model. Strong multilingual and tool-use performance for its size, Apache-2.0 licensed.
Mistral Nemo is a efficient AI model from Mistral. It costs $0.150 per million input tokens and $0.150 per million output tokens (blended $0.150/M), with a 128,000-token context window.
0.0%over 87 days · hover to read
- Open weights
- Multilingual
- 128K context
- Tool use
- Multilingual self-hosted chat
- Function calling on small hardware
Benchmarks
More from Mistral
See all 15 →Price history
1 recorded change| Date | Rate | Was | Now | Change |
|---|---|---|---|---|
| 17 Jul 2026 | Input | $0.020 | $0.019 | -5% |
Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.
Frequently asked questions
How much does Mistral Nemo cost?
Mistral Nemo costs $0.150 per million input tokens and $0.150 per million output tokens, for a blended reference rate of $0.150 per million tokens.
What is Mistral Nemo's context window?
Mistral Nemo supports up to 128,000 tokens of context in a single request.
What is Mistral Nemo best for?
Mistral Nemo is well suited to Open weights, Multilingual and 128K context.
Who makes Mistral Nemo?
Mistral Nemo is developed and served by Mistral. It was released in Jul 2024.