GLM 5.3

glm-5.3

Z.aiDegraded

Specifications

Context window
1000K tokens
Max output
65K tokens
Input price
$1.400 / 1M tokens
Output price
$4.400 / 1M tokens
Cache read price
$0.260 / 1M tokens

Live status

Uptime 24h
98.86%
Uptime 7d
99.79%
Error rate
1.14%
Avg latency
2725 ms