particle-ai: Particle-1
particle-ai/particle-1
Try Particle-1 for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "particle-ai/particle-1"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "particle-ai/particle-1"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Particle-1 is a chat model from Particle, post-trained from DeepSeek V4.1 Flash with reinforcement learning that rewards solving a task in fewer tokens. Particle says it uses about 45% fewer tokens on average, and this first release targets software engineering.
In Particle's own tests on Terminal-Bench 2.1, ReactBench, ADE Bench and DeepSWE 1.1, it produced 28.4% to 52.2% fewer output tokens and cost 34.4% to 51.6% less per task than DeepSeek V4.1 Flash, with pass@1 within the base model's confidence intervals. Its general benchmark scores stay close to the base model, such as 90.40% on GPQA Diamond (base 90.91%) and 86.08% on MMLU (base 85.98%). Particle attributes most of the savings to shorter reasoning, stopping once a task is done, and fewer trial-and-repair cycles.
It accepts text and image input, returns text, has a 1,048,576-token context window and 131,072 max output tokens, and supports tool calling. It suits coding agents and other tool-calling workflows where fewer output tokens lower the cost per task.
Context Window 1M
tokens
Max Output 131K
tokens
Input Cost $0.25
per million tokens
Output Cost $1
per million tokens
Input text, image
modalities
Tool Use Yes
Release Date Oct 29, 2026
Try Particle-1 for free
Try Particle-1 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Particle-1 by particle-ai through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Particle-1 is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Particle-1 is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.25 |
| Output | $1 |
Particle-1 was created by particle-ai and released on Oct 29, 2026.
Particle-1 supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,097 pages of text.
Particle-1 can generate up to 131K tokens in a single response.
Particle-1 accepts the following input types: text, image. It produces: text.
Yes, Particle-1 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Particle-1 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Particle-1 to your app for free
Developers can integrate Particle-1 for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.