by Zhipu AI

GLM 5.2.

text open weights datacenter 753B params 1M ctx
Cheapest input
$0.007/M
on OpenRouter
Cheapest output
$2.4/M
on DeepInfra
Smallest GPU
8× Nvidia A100 SXM4
$5.73/hr

Open-weights text model from Z.ai for long-horizon coding and agent work, with a one million token context and adjustable thinking effort, under the MIT licence.

Smallest GPU to run it See all quantisations →

8× Nvidia A100 SXM4 · $5.73/hr.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it Top 3 cheapest · 6 total below

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.007 $6.8 Launch ↗
DeepInfra hosted inference $0.75 $2.4 Launch ↗
Together AI hosted inference $1.4 $4.4 Launch ↗
Sources

Official references.

Family

Variants in the GLM family.

FAQ

Frequently asked.

How do I run GLM 5.2?
GLM 5.2 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access GLM 5.2?
GLM 5.2 is available via Together AI, DeepInfra, OpenRouter, z.ai. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run GLM 5.2?
API pricing starts at $0.007/M input tokens and $6.8/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is GLM 5.2 open-source or proprietary?
GLM 5.2 is open-weight under the mit license. You can download and self-host it.