Mistral Small 3.2 24B
Mistral Small 3.2 24B is an AI model developed by Mistral designed for instruction following and function calling. It supports both text and image inputs and features a 256,000 token context window.
Mistral Small 3.2 24B specs and pricing
- Provider: Mistral
- Released: June 20, 2025
- Context window: 256K tokens
- Max output: 16K tokens
- Input: images, text
- Output: text
- Price: $0.075 input / $0.20 output per 1M tokens
- Tool calling: yes
What Mistral Small 3.2 24B is good at
- Tasks requiring precise instruction following
- Applications that rely on tool or function calling
- Analyzing documents and images within a single session
To-dos to try with Mistral Small 3.2 24B
- Upload a series of images and ask the model to describe the visual differences between them.
- Provide a set of API documentation and ask the model to write a function call based on specific user requirements.
- Paste a long document and ask the model to extract key information while adhering to strict formatting instructions.
FAQ
- What kind of inputs can Mistral Small 3.2 24B process? This model is capable of processing both text and image inputs.
- What is the primary focus of this model? It is optimized for accurate instruction following, reducing repetition, and improving function calling capabilities.
- How much does Mistral Small 3.2 24B cost? Mistral Small 3.2 24B costs $0.075 per million input tokens and $0.20 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.24 credits ($1 = 100 credits).
- What is the context window of Mistral Small 3.2 24B? Mistral Small 3.2 24B can read up to 256K tokens at once and write up to 16K tokens in one reply.
- Can I use Mistral Small 3.2 24B without coding? Yes. In todo.is you pick Mistral Small 3.2 24B 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.