Mistral Nemo
Mistral Nemo is a 12B parameter model developed by Mistral in collaboration with NVIDIA. It features a large 128k token context window and is designed for multilingual text processing and tool-calling tasks.
Mistral Nemo specs and pricing
- Provider: Mistral
- Released: July 19, 2024
- Context window: 131K tokens
- Max output: 16K tokens
- Input: text
- Output: text
- Price: $0.029 input / $0.03 output per 1M tokens
- Tool calling: yes
What Mistral Nemo is good at
- Processing long multilingual documents
- Integrating AI into applications via tool-calling
- Generating text in multiple languages including Chinese and Japanese
To-dos to try with Mistral Nemo
- Translate this 50-page technical manual from English to French while maintaining formatting
- Analyze a long transcript and use a tool to add identified action items to a calendar
- Summarize a series of documents written in Spanish and German into a single English report
FAQ
- Who developed Mistral Nemo? Mistral Nemo was built by Mistral in collaboration with NVIDIA.
- What languages does this model support? The model is multilingual and supports English, French, German, Spanish, Italian, Portuguese, Chinese, and Japanese.
- How much does Mistral Nemo cost? Mistral Nemo costs $0.029 per million input tokens and $0.03 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.09 credits ($1 = 100 credits).
- What is the context window of Mistral Nemo? Mistral Nemo can read up to 131K tokens at once and write up to 16K tokens in one reply.
- Can I use Mistral Nemo without coding? Yes. In todo.is you pick Mistral Nemo as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.