reroute

Z.ai: GLM 5.2

z-ai/glm-5.2

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,...

Modalities
In / Out Price
$0.03 / $10 per 1M
Context
1M
Released
Jun 16, 2026
Knowledge Cutoff
—

Providers

Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.

ProviderContextInput /MOutput /MCache read /MLatencyThroughputUptime
Relace1M$0.03$10$0.03——100.00%
Wafer1M$0.084$4.30$0.083——100.00%
Wafer1M$0.19$4.30$0.18——100.00%
InferenceNetfp41M$0.20$4.40$0.13——100.00%
Decartmxfp41M$0.279$1.72$0.107——100.00%
Morphfp81M$0.309$3.74$0.137——100.00%
Baidufp41M$0.56$1.96$0.139——100.00%
DeepInfrafp41M$0.563$1.80$0.105——100.00%
StreamLakefp81M$0.643$2.02$0.119——100.00%
Novitafp81M$0.65$2.04$0.121——100.00%
DigitalOcean1M$0.70$2.20$0.105——100.00%
CoreWeavefp41M$0.76$2.42$0.14——100.00%
AtlasCloudfp81M$0.938$2.95$0.174——100.00%
Alibabafp81M$0.966$3.04$0.193——95.65%
Cloudflare262K$1.18$4.40$0.26———
SiliconFlowfp81M$1.19$3.74$0.221——100.00%
Phalafp81M$1.26$3$0.22——100.00%
Inceptronfp41M$1.39$4.39$0.25——100.00%
Nebiusfp41M$1.40$4.40———90.00%
Mistralnvfp41M$1.40$4.40$0.14——100.00%
BaseTenfp81M$1.40$4.40$0.14——100.00%
Together1M$1.40$4.40$0.26——100.00%
Baidufp81M$1.40$4.40$0.26——100.00%
BaseTenfp81M$1.40$4.40$0.14——100.00%
Venicefp81M$1.40$4.40$0.26——100.00%
GMICloudfp81M$1.40$4.40$0.26——100.00%
Parasailfp4262K$1.40$4.40$0.26——100.00%
Friendli1M$1.40$4.40$0.26——100.00%
Z.AIfp81M$1.40$4.40$0.26——100.00%
Mistral1M$1.54$4.84$0.154———
BaseTenfp81M$2.10$6.60$0.21——100.00%
BaseTenfp81M$2.10$6.60$0.21——100.00%
Decartfp41M$2.25$8$0.48——100.00%
Alibabafp81M$2.31$7.26$0.462——100.00%