Nothing
leaves.

GLM-5.2 on your hardware. No egress, no cloud, no external provider.

Request deployment
01

Specification

Deployment includes 4x NVIDIA GB10 variants running GLM-5.2, accessible via a local inference endpoint. No requests leave the customer network.

ModelGLM-5.2
Hardware4x NVIDIA GB10
Throughput~30 tokens/s
EgressNone
02

Pricing

One-time deployment fee.

Deployment
$25,000
03

Contact

Request a deployment or ask a question.