Claude Opus 4.7 Is Now Available in Puter.js

Puter.js now supports Claude Opus 4.7, Anthropic's most capable generally available model—built for complex reasoning, agentic coding, and long-horizon autonomous tasks.

What is Claude Opus 4.7?

Claude Opus 4.7 is Anthropic's latest flagship model, released on April 16, 2026. It delivers a step-change improvement in long-horizon agentic work over its predecessor Opus 4.6, along with strong gains in knowledge work, vision, and file-system-based memory.

Key highlights:

• 1 million token context window — process entire codebases, lengthy documents, and complex datasets in a single prompt, now with a new tokenizer
• 128,000 output tokens — generate substantially longer responses for detailed analyses and code generation
• Adaptive thinking — the model autonomously decides when and how much to reason, adjusting depth to task complexity
• High-resolution image input — first Claude model with high-res vision support, up to 2576px / 3.75MP with 1:1 pixel coordinate mapping
• New xhigh effort level — a dedicated effort parameter for demanding coding and agentic use cases
• Task budgets (beta) — lets the model self-moderate token usage across an agentic loop with a running countdown

What's New Compared to Opus 4.6?

Opus 4.7 introduces several major upgrades:

• Better agentic coding — significantly improved at long-horizon, multi-step coding workflows where the model operates autonomously
• Enhanced knowledge work — meaningful gains in document redlining, presentation editing, chart/figure analysis, and pixel-level data transcription
• File-system memory — better at writing and using scratchpads, notes files, and structured memory stores across long tasks
• More direct communication — calibrates response length to task complexity, uses fewer tool calls by default, and provides regular progress updates during long traces

Examples

Complex Reasoning

puter.ai.chat(
  `A company has 3 departments. Department A's budget is 20% more than B's.
  Department C's budget is 15% less than A and B combined.
  If the total budget is $14 million, calculate each department's budget.
  Show your step-by-step reasoning.`,
  { model: 'claude-opus-4-7' }
);

Agentic Code Review

puter.ai.chat([
  { role: "user", content: largeCodebase + "\n\nReview this codebase for security vulnerabilities, performance bottlenecks, and architectural issues. Prioritize findings by severity." }
], { model: 'claude-opus-4-7' });

Streaming

const response = await puter.ai.chat(
  "Design a distributed task scheduler with fault tolerance and exactly-once execution guarantees",
  { model: 'claude-opus-4-7', stream: true }
);

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

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 and no infrastructure setup. Start building with Claude Opus 4.7 immediately.

Learn more:

• Free, Unlimited Claude API
• Puter.js AI Documentation