Model facet · Providers

GLM-5.3 inference providers

GLM-5.3 is currently served Z.ai-first-party and through a small number of direct-routed platforms. This page tracks who serves it, at what price, with what provenance — expect more providers to add it over time, as happened with GLM-5.2.

Tracked providers

Live provider data could not be refreshed for this build. Showing the last verified snapshot.

ProviderInput /1M tokensOutput /1M tokensProvenance
Z.ai$1.40$4.40vendor reported
OpenRouter$1.40$4.40verified
Vercel AI Gateway$1.40$4.40verified

How to read this table

Each row is labeled by provenance: independently verified listings versus a provider’s own vendor-reported number. Routing, quantization, and uptime can all change — record the provider and date alongside any benchmark or latency claim you rely on.

Ready to test the workflow?

Create account & add credits

Current routing reality

At launch, GLM-5.3 is Z.ai-first-party and direct-routed through OpenRouter and Vercel AI Gateway. Third-party inference hosts that carried GLM-5.2 (DeepInfra, Novita, Fireworks, SiliconFlow) are expected to add GLM-5.3 on a similar timeline, not guaranteed on any specific date.

Frequently asked questions

Where is the live GLM-5.3 model page?

The canonical model page with current OneInfer pricing, capabilities, and availability is /models/zai-org/GLM-5.3. This page is a focused facet of that entity, not a replacement for it.

How should I treat benchmark or price claims?

Check each claim’s provenance label and observed date. Vendor-reported and independently verified numbers are shown as separate evidence classes on this hub.

Put GLM-5.3 to work

Fund a controlled evaluation, start with a prepared prompt, and measure quality and cost on your own workload.