GLM 5.1 Is Now Available in Puter.js

Puter.js now supports GLM-5.1, Z.AI's frontier-class reasoning model that surpasses GPT-5.4 and Claude Opus 4.6 on SWE-Bench Pro, making it the top-performing open-weight model for coding and agentic tasks.

What is GLM-5.1?

GLM-5.1 is a post-training refinement of GLM-5 focused on coding and agentic performance. It shares the same 744B-parameter Mixture of Experts architecture (40B active per token) but pushes the boundaries on real-world software engineering benchmarks. Key highlights include:

• SWE-Bench Pro Leader: Scores 58.4% on SWE-Bench Pro, surpassing GPT-5.4 (57.7%) and Claude Opus 4.6 (57.3%) among open-weight models
• Strong Math Reasoning: Achieves 95.3 on AIME 2026, demonstrating advanced mathematical problem-solving
• 200K Context Window: Process massive codebases and generate outputs up to 200K tokens
• Long-Horizon Agentic Workflows: Can stay on a single task for up to 8 hours—planning, executing, testing, and iterating before returning production-ready output

Examples

Complex software engineering

puter.ai.chat(`Refactor this legacy Express.js API to use a clean architecture pattern 
with proper dependency injection, error handling middleware, and request validation:
${legacyCode}`,
  { model: 'z-ai/glm-5.1', stream: true }
);

Multi-step agentic coding

puter.ai.chat(`Analyze this codebase for performance bottlenecks, then:
1. Identify the top 5 slowest database queries
2. Suggest optimized versions with proper indexing
3. Write migration scripts for the schema changes
4. Generate load tests to verify the improvements`,
  { model: 'z-ai/glm-5.1' }
);

Advanced reasoning

puter.ai.chat("Solve AIME 2026 Problem 12 step by step, showing all intermediate reasoning",
  { model: 'z-ai/glm-5.1' }
);

Long context code review

puter.ai.chat(`Review this entire repository and generate a comprehensive security audit report
covering OWASP Top 10 vulnerabilities, dependency risks, and authentication flaws:
${entireRepo}`,
  { model: 'z-ai/glm-5.1' }
);

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-5.1 immediately.

Learn more:

• Free, Unlimited Z.AI GLM API
• Puter.js AI Documentation