Ship a Full-Stack App with One Prompt

Copy this prompt into your AI coding agent, or open it in one below.

Give this to your AI Create a to-do list app using Puter.js

Coding manually? see the guide

Blog

Arcee AI Trinity Large Thinking Is Now Available in Puter.js

On this page

Puter.js now supports Trinity Large Thinking, Arcee AI's reasoning-optimized model that ranks #2 on PinchBench behind only Claude Opus 4.6—at roughly 96% lower cost.

What is Trinity Large Thinking?

Trinity Large Thinking is a reasoning-optimized open-source model from Arcee AI, built on a 398B-parameter sparse Mixture-of-Experts architecture with approximately 13B active parameters per token. Key features include:

  • Extended Chain-of-Thought Reasoning: Uses explicit thinking traces before generating responses for more accurate, well-reasoned outputs
  • 262K Context Window: Supports up to 262K tokens of input with up to 80K output tokens
  • Top Agentic Performance: Scores 94.7% on τ²-Bench and 91.9% on PinchBench, ranking #2 overall behind only Claude Opus 4.6
  • Purpose-Built for Agents: Designed for multi-turn tool calling, long-horizon planning, and stable behavior across extended agent loops

Examples

Complex reasoning with thinking traces

const response = await puter.ai.chat(
  "Prove that the square root of 2 is irrational",
  { model: 'arcee-ai/trinity-large-thinking', stream: true }
);

for await (const part of response) {
  if (part?.reasoning) puter.print(part?.reasoning);
  else puter.print(part?.text);
}

Agentic tool use

puter.ai.chat("Find the current weather in Tokyo and convert the temperature from Celsius to Fahrenheit",
  { model: 'arcee-ai/trinity-large-thinking' }
);

Code generation with reasoning

puter.ai.chat("Implement a B-tree in Python with insert, delete, and search operations. Explain your design choices.",
  { model: 'arcee-ai/trinity-large-thinking' }
);

Multi-step analysis

puter.ai.chat("Compare the CAP theorem trade-offs of Cassandra, MongoDB, and CockroachDB for a global e-commerce platform",
  { model: 'arcee-ai/trinity-large-thinking' }
);

Get Started Now

Just add one library to your project:

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

Or add one script tag to your HTML:

<script src="https://js.puter.com/v2/"></script>

No API keys needed. Start building with Trinity Large Thinking immediately.

Learn more:

Ship a Full-Stack App with One Prompt

Give this to your AI Create a to-do list app using Puter.js

Coding manually? see the guide