Mistral Medium 3.5
Mistral Medium 3.5 is a dense 128B instruction-following model developed by Mistral AI. It is designed to handle complex reasoning tasks, coding projects, and agentic workflows using both text and image inputs.
Mistral Medium 3.5 specs and pricing
- Provider: Mistral
- Released: April 30, 2026
- Context window: 262K tokens
- Max output: 210K tokens
- Input: text, images, files
- Output: text
- Price: $1.50 input / $7.50 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Mistral Medium 3.5 is good at
- Complex reasoning and problem-solving tasks
- Software development and coding assistance
- Multi-modal analysis involving text and images
To-dos to try with Mistral Medium 3.5
- Analyze a set of architectural diagrams and provide a summary of the structural requirements.
- Debug a complex code repository by identifying logic errors across multiple files.
- Formulate a multi-step project plan based on a provided document and a series of reference images.
FAQ
- What types of input can Mistral Medium 3.5 process? The model supports text, image, and file inputs to generate text-based outputs.
- What is the primary design focus of this model? It is specifically built for agentic workflows, complex reasoning, and coding tasks.
- How much does Mistral Medium 3.5 cost? Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 5.25 credits ($1 = 100 credits).
- What is the context window of Mistral Medium 3.5? Mistral Medium 3.5 can read up to 262K tokens at once and write up to 210K tokens in one reply.
- Can I use Mistral Medium 3.5 without coding? Yes. In todo.is you pick Mistral Medium 3.5 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.