← LLM API prices

GLM 5.2

Zhipu

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

In
$1.40
Out
$4.40
Blended
$2.15
Where to buy this model
23 access routes
RouteInOutBlendedvs
DeepInfra cheapestfp4$0.49$1.56$0.76-
StreamLake fp8$0.56$1.76$0.86+13%
Ambient fp8$0.60$2.00$0.95+25%
Novita fp8$0.68$2.15$1.05+38%
DigitalOcean $0.70$2.20$1.08+42%
CoreWeave fp4$0.76$2.42$1.18+55%
AtlasCloud fp8$0.94$2.95$1.44+89%
Alibaba fp8$0.97$3.04$1.48+95%
Inceptron fp4$1.10$2.99$1.57+107%
Phala fp8$1.26$3.00$1.70+124%
SiliconFlow fp8$1.19$3.74$1.83+141%
Mistral $1.40$4.40$2.15+183%
BaseTen fp8$1.40$4.40$2.15+183%
Together $1.40$4.40$2.15+183%
Baidu fp8$1.40$4.40$2.15+183%
Fireworks $1.40$4.40$2.15+183%
Venice fp8$1.40$4.40$2.15+183%
GMICloud fp8$1.40$4.40$2.15+183%
Parasail fp4$1.40$4.40$2.15+183%
Friendli $1.40$4.40$2.15+183%
Cloudflare $1.40$4.40$2.15+183%
Z.AI fp8$1.40$4.40$2.15+183%
Decart fp4$2.10$6.60$3.23+325%

official API · cloud platform · inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.

Ctx
1.048576M
max output
128K
cache read /1M
$0.14
Family
glm
Modalities
text
Features
json · reasoning · tools

Live pricing, updated 2026-09-15.

Concepts on this page