GLM-5
Specifications
- Input
- Output
- Context window
- 203K tokens
- Released
- Feb 2026
Performance
- Speed
- 32 t/s
- TTFT
- 3.2s
- Latency
- 849 ms
- Intelligence
- —
Pricing
- Input
- €0.95 per 1M tokens
- Output
- €2.95 per 1M tokens
About this model
ZAI's frontier 744B MoE model (40B activated) with 203K context. Excels at agentic engineering, coding (SWE-bench 77.8%), reasoning, and tool use. Built with asynchronous RL and MIT licensed.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- Hybrid Default on
Knowledge horizon
Released Feb 2026
Today
Since release 5 mo
See also
Add Model to Comparison
Search for a model to add