Mistral Large
Mistral Large is a proprietary model developed by Mistral AI designed for complex reasoning, coding, and structured data tasks. It supports both text and file inputs and features a large context window to handle extensive information.
Mistral Large specs and pricing
- Provider: Mistral
- Released: February 26, 2024
- Context window: 128K tokens
- Max output: 102K tokens
- Input: text, files
- Output: text
- Price: $2.00 input / $6.00 output per 1M tokens
- Tool calling: yes
What Mistral Large is good at
- Generating and debugging complex code
- Extracting structured data into JSON format
- Analyzing long documents and files
To-dos to try with Mistral Large
- Upload a technical document and ask the model to extract key data points into a JSON object
- Paste a block of code and ask the model to identify bugs and suggest optimizations
- Provide a long report and ask for a summary of the main arguments presented
FAQ
- What is Mistral Large primarily designed to do? It is built to excel at reasoning, coding, chat, and generating structured output like JSON.
- Can I upload files for the model to analyze? Yes, the model accepts both text and file inputs.
- How much does Mistral Large cost? Mistral Large costs $2.00 per million input tokens and $6.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 6.44 credits ($1 = 100 credits).
- What is the context window of Mistral Large? Mistral Large can read up to 128K tokens at once and write up to 102K tokens in one reply.
- Can I use Mistral Large without coding? Yes. In todo.is you pick Mistral Large 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.