Particle-1 (free)
Particle-1 is a free, agentic coding model developed by Particle AI and post-trained on DeepSeek V4.1 Flash. It is designed for software engineering tasks, featuring a large context window and the ability to process both text and image inputs.
Particle-1 (free) specs and pricing
- Provider: Particle AI
- Released: October 28, 2026
- Context window: 1M tokens
- Max output: 131K tokens
- Input: text, images
- Output: text
- Price: free
- Reasoning: yes
- Tool calling: yes
What Particle-1 (free) is good at
- Managing complex terminal workflows
- Implementing codebase changes
- Analyzing software-related data
To-dos to try with Particle-1 (free)
- Read this entire codebase and identify potential security vulnerabilities in the authentication module.
- Analyze these screenshots of a UI bug and generate the necessary CSS and HTML fixes.
- Execute a series of terminal commands to refactor the project directory structure and update the build configuration.
FAQ
- What is the primary purpose of the Particle-1 model? Particle-1 is a token-efficient model specifically built to assist with software engineering tasks, including coding and terminal-based workflows.
- Can this model process visual information? Yes, Particle-1 supports both text and image inputs, allowing it to analyze visual data alongside code.
- How much does Particle-1 (free) cost? Particle-1 (free) is available as a free model. In todo.is it doesn't use credits, though free models can be rate-limited by the provider.
- What is the context window of Particle-1 (free)? Particle-1 (free) can read up to 1M tokens at once and write up to 131K tokens in one reply.
- Can I use Particle-1 (free) without coding? Yes. In todo.is you pick Particle-1 (free) 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.