Model Square
Zhipu

glm-5.3-flashx

智谱·Usage-based billing
TPS
—
Average latency
—
Success rate
—

Pricing

Base Price

Input
$0.3/ 1M
Output
$1.05/ 1M
Cache Read$0.085/ 1M
Cache Write$0.375/ 1M
Cache Write (1h)$0.6/ 1M
Image In$0.3/ 1M
Audio In$0.3/ 1M
Audio Out$0.3/ 1M

Model

Provider智谱
TypeUsage-based billing
Groups
maas测试
Endpoints
openaiopenai-response-compact
glm-5.3-flashx