Mistral Medium 3
Mistral Medium 3 is an enterprise-grade model developed by Mistral that supports both text and image inputs. It is designed to provide high-performance capabilities while maintaining a lower operational cost compared to other frontier models.
Mistral Medium 3 specs and pricing
- Provider: Mistral
- Released: May 7, 2025
- Context window: 131K tokens
- Max output: 105K tokens
- Input: text, images, files
- Output: text
- Price: $0.44 input / $2.20 output per 1M tokens
- Tool calling: yes
What Mistral Medium 3 is good at
- Analyzing documents and images for enterprise tasks
- Integrating AI into applications via tool calling
- Processing large volumes of text and visual data
To-dos to try with Mistral Medium 3
- Analyze a set of uploaded product images and draft a descriptive catalog entry for each.
- Summarize a long technical document and extract key action items into a structured list.
- Use tool calling to connect the model to a database and retrieve specific customer data based on a natural language query.
FAQ
- What types of media can Mistral Medium 3 process? The model is multimodal and can process text, images, and files as input.
- Does this model support external tool integration? Yes, Mistral Medium 3 features built-in support for tool calling.
- How much does Mistral Medium 3 cost? Mistral Medium 3 costs $0.44 per million input tokens and $2.20 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.54 credits ($1 = 100 credits).
- What is the context window of Mistral Medium 3? Mistral Medium 3 can read up to 131K tokens at once and write up to 105K tokens in one reply.
- Can I use Mistral Medium 3 without coding? Yes. In todo.is you pick Mistral Medium 3 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.