GLM-4.5
Z.ai's general-purpose flagship trained on 22 trillion tokens
GLM-4.5
Z.ai • July 2025
Training Data
22 trillion tokens
GLM-4.5
July 2025
Parameters
~200 billion
Training Method
Multi-stage Fine-tuning
Context Window
128,000 tokens
Knowledge Cutoff
June 2025
Key Features
Reasoning Focus • Agentic Capabilities • Open Weights • Multilingual
Capabilities
Reasoning: Excellent
Agentic: Very Good
General Knowledge: Excellent
What's New in This Version
Specialized fine-tuning combining reasoning, agentic, and knowledge capabilities
Z.ai's general-purpose flagship trained on 22 trillion tokens
What's New in This Version
Specialized fine-tuning combining reasoning, agentic, and knowledge capabilities
Technical Specifications
Key Features
Capabilities
Other Z.ai Models
Explore more models from Z.ai
GLM-5.3
Z.ai's flagship on GLM-5.2's base, with every gain from scaled-up post-training — frontier-level coding and cyber-defense capability
GLM-5.3-Flash
Z.ai's MIT-licensed efficient model — natively multimodal, with hybrid sparse and linear attention far cheaper to run than GLM-5.3
GLM-5.2
Zhipu AI's MIT-licensed flagship extending GLM-5.1 to a 1M-token context, the highest-ranked open-source model on long-horizon coding benchmarks
