Model Square
Zhipu

glm-5.3-flash

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

Pricing

Base Price

Input
$0.15/ 1M
Output
$0.5/ 1M
Cache write$0.03/ 1M

Pricing by Group

GroupRatioInputOutputCache Write
default
2x
$0.3
$1
$0.06

Prices shown per 1M tokens

Model

Provider智谱
TypeUsage-based billing
Groups
default
Endpoints
openaiopenai-response
glm-5.3-flash