Tracked providers
Live provider data could not be refreshed for this build. Showing the last verified snapshot.
| Provider | Input /1M tokens | Output /1M tokens | Provenance |
|---|---|---|---|
| Z.ai | $1.40 | $4.40 | vendor reported |
| OpenRouter | $1.40 | $4.40 | verified |
| Vercel AI Gateway | $1.40 | $4.40 | verified |
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 creditsCurrent 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.