Mistral Large 4
Mistral Large 4 is a multimodal model developed by Mistral AI designed for complex reasoning, coding, and agentic tasks. It supports both text and image inputs and features a large 1-million-token context window.
Mistral Large 4 specs and pricing
- Provider: Mistral
- Released: October 6, 2026
- Context window: 1M tokens
- Max output: 262K tokens
- Input: text, images
- Output: text
- Price: $1.36 input / $4.18 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Mistral Large 4 is good at
- Complex reasoning and problem-solving tasks
- Analyzing documents and images together
- Building and executing agentic workflows
To-dos to try with Mistral Large 4
- Upload a series of technical diagrams and ask the model to explain the relationship between the components.
- Paste a large codebase and request a summary of the architectural logic.
- Provide a long-form research report and ask the model to extract key data points into a structured format.
FAQ
- What types of input does Mistral Large 4 support? The model supports both text and image inputs.
- What is Mistral Large 4 primarily designed to do? It is built for reasoning, coding, and agentic workloads.
- How much does Mistral Large 4 cost? Mistral Large 4 costs $1.36 per million input tokens and $4.18 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 4.39 credits ($1 = 100 credits).
- What is the context window of Mistral Large 4? Mistral Large 4 can read up to 1M tokens at once and write up to 262K tokens in one reply.
- Can I use Mistral Large 4 without coding? Yes. In todo.is you pick Mistral Large 4 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.