Blog

GLM 5 Is Now Available in Puter.js

On this page

Puter.js now supports GLM-5, Z.AI's fifth-generation flagship model that approaches Claude Opus 4.5-level capability with full open-weight availability.

What is GLM-5?

GLM-5 is Z.AI's most powerful model to date, featuring a 744 billion parameter Mixture of Experts architecture with 256 experts and only 40B active parameters per inference. Key highlights include:

  • 200K Context Window: Process massive documents and generate outputs up to 131K tokens
  • Top-Tier Coding: Scores 77.8% on SWE-bench Verified, approaching Claude Opus 4.5's 80.9%
  • Strong Reasoning: Scores 50.4 on Humanity's Last Exam and ranks #1 on BrowseComp at 75.9
  • Agentic Intelligence: Built-in task decomposition, tool orchestration, and workflow execution

Examples

Complex reasoning

puter.ai.chat("Prove that the square root of 2 is irrational using proof by contradiction",
  { model: 'z-ai/glm-5' }
);

Agentic task planning

puter.ai.chat(`I need to build a full-stack e-commerce app. Break this down into:
1. Architecture decisions
2. Database schema design
3. API endpoints needed
4. Frontend component hierarchy`,
  { model: 'z-ai/glm-5', stream: true }
);

Code generation

puter.ai.chat("Implement a concurrent web crawler in Python with rate limiting, retry logic, and result deduplication",
  { model: 'z-ai/glm-5' }
);

Long context processing

puter.ai.chat(`Analyze this entire codebase and identify potential security vulnerabilities:
${largeCodebase}`,
  { model: 'z-ai/glm-5' }
);

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 GLM-5 immediately.

Learn more:

Free, Serverless AI and Cloud

Start creating powerful web applications with Puter.js in seconds!

Get Started Now

Read the Docs Try the Playground