Particle-1
Particle-1 is a large language model made by Particle AI, added to the catalog on 28 Oct 2026. It has a context window of 1,048,576 tokens and costs $0.07 per 1M input tokens and $0.50 per 1M output tokens. It accepts text and images and produces text. Typical uses: terminal-based software engineering, making codebase changes and working with coding instructions that include images.
Price checked ยท source: OpenRouter
What Particle-1 is
Particle-1 is a token-efficient, agentic coding model from Particle AI for software engineering work. The catalog names terminal workflows and codebase changes as areas it is suited to, and says it is post-trained on DeepSeek V4.1 Flash. It accepts text and images and produces text. Alongside these input and output modalities, it supports reasoning, tools, structured outputs, and response-format controls. These details describe a model centered on coding tasks, with options for tool-supported work and for requesting responses in a defined structure.
Particle-1 has a context window of 1,048,576 tokens and a maximum output of 131,072 tokens. The context capacity is relevant when a task needs extensive material to be considered together, including lengthy instructions or substantial code-related text. The output limit allows for long text responses when a coding task calls for detailed results. Since image input is listed but image output is not, the catalog describes images as an input modality and text as the model's output. Tool support is listed, but the catalog does not name particular tools or integrations. Structured output and response-format support offer ways to request responses in a defined form. The catalog also does not specify programming languages, supported file types, or the exact terminal workflow. Its stated scope is clearest for terminal-based software engineering and codebase changes, while other implementation details remain unspecified.
Key features
- Accepts text and image inputs and produces text
- Has a context window of 1,048,576 tokens
- Supports tools, reasoning, structured outputs, and response formats
- Allows outputs of up to 131,072 tokens
- Described for terminal workflows and codebase changes
Typical uses
- Terminal-based software engineering
- Making codebase changes
- Working with coding instructions that include images
- Generating structured text for coding workflows
Particle-1 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Free |
|---|---|---|
| Input, per 1M tokens | $0.07 | $0 |
| Output, per 1M tokens | $0.50 | $0 |
| Cached input read, per 1M tokens | $0.03 | n/a |
| Variant | Model id |
|---|---|
| Free | particle-ai/particle-1:free |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
The price last changed on 22 Nov 2026. One price change has been recorded since Particle-1 was added.
| Date | Input /1M | Output /1M | Change |
|---|---|---|---|
| $0.07 | $0.50 | Price changed | |
| $0.07 | $0.50 | Added at this price |
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0022 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0031 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.011 |
Particle-1 specifications
| Model id | particle-ai/particle-1 |
|---|---|
| Version | particle-1-20261027 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 131,072 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 28 Oct 2026 |
| Input types | text, image |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Particle-1 yet.