glm-5.1

智谱·Dynamic billing

TPS

—

Average latency

—

Success rate

—

Pricing

Base Price

Input

$0.888889/ 1M

Output

$3.5556/ 1M

Cache Read$0.192593/ 1M

Dynamic billing

Prices vary by usage tier and request conditions

Tiered price table

0_32k

Length < 32K

Input

$0.8889 / 1M

Output

$3.5556 / 1M

Cache Read

$0.1926 / 1M

32k_plus

Input

$1.1852 / 1M

Output

$4.1481 / 1M

Cache Read

$0.2963 / 1M

Tier	Input	Output	Cache Read
0_32k Length < 32K	$0.8889 / 1M	$3.5556 / 1M	$0.1926 / 1M
32k_plus	$1.1852 / 1M	$4.1481 / 1M	$0.2963 / 1M

Model

Provider智谱

TypeDynamic billing

Groups

Glm_官Kimi_官Minimax_官Qwen_官maas测试业务线-测试环境业务线-生产环境

Endpoints

openai

glm-5.1