Particle-1
Particle-1 is a coding model from Particle AI, post-trained on DeepSeek V4.1 Flash for software engineering and agent workflows. It supports reasoning and tool calling, accepts text and images, and has a 1,048,576-token context window.
Particle-1 specs and pricing
- Provider: Particle AI
- Released: October 28, 2026
- Context window: 1M tokens
- Max output: 131K tokens
- Input: text, images
- Output: text
- Price: $0.25 input / $1.00 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Particle-1 is good at
- Terminal workflows
- Codebase changes
- Working with text and images
To-dos to try with Particle-1
- Inspect this codebase and identify where the login flow is implemented.
- Review this terminal error and suggest a code change to address it.
- Describe the interface shown in this screenshot.
FAQ
- Who makes Particle-1? Particle-1 is made by Particle AI. It was post-trained on DeepSeek V4.1 Flash.
- Can Particle-1 read images? Yes. Particle-1 accepts both image and text input and produces text output.
- How much does Particle-1 cost? Particle-1 costs $0.25 per million input tokens and $1.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.84 credits ($1 = 100 credits).
- What is the context window of Particle-1? Particle-1 can read up to 1M tokens at once and write up to 131K tokens in one reply.
- Can I use Particle-1 without coding? Yes. In todo.is you pick Particle-1 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.