Skip to content

Model catalogGLM

GLM-4 9B

Lightest and cheapest — everyday chat and quick tasks. Served with vLLM behind your own private, OpenAI-compatible /v1 endpoint — billed by the second, terminate anytime.

9B dense · bf16 · 128K context · 1× 24 GB · per-second billing

01Specifications

The specs the launcher enforces.

Architecture, served precision, max context, and the minimum GPU shape — the numbers that decide how GLM-4 9B runs and what it costs.

SpecValue
Architecture9B dense
Served precisionbf16
Max context128K
Minimum GPU shape1× 24 GB

Runs on 1× 24 GB · billed per second — final cost depends on the GPU shape.

Full pricing →

02How it runs

A private endpoint, not a shared API.

Launching GLM-4 9B runs the model on your own instance and gives you a private, OpenAI-compatible /v1 endpoint and API key. Point any OpenAI-compatible SDK at your base URL, change the model name, and existing code works. The endpoint is yours alone — terminate the instance and it goes away with it.

Billing is by the second on the 1× 24 GB shape the launcher enforces, from boot to terminate. No commitment and no tier gates.

03Get started

Launch GLM-4 9B now.

One private OpenAI-compatible endpoint, one key, billed by the second. The console opens with GLM-4 9B preselected.