Details
A lower-latency, higher-throughput serving tier of GLM-5.2 for faster responses at a higher price.
Context window
1M tokens
Max output
4.1K tokens
Provider
Z-AI
Pricing
Premium
PDF support
No
Zero Data Retention
Yes
Added
June 23, 2026
A lower-latency, higher-throughput serving tier of GLM-5.2 for faster responses at a higher price.
Context window
1M tokens
Max output
4.1K tokens
Provider
Z-AI
Pricing
PDF support
Zero Data Retention
Added
June 23, 2026