Z.ai: GLM 5.2 (batch)
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Everything else
| Max output | — |
|---|---|
| Input / 1M | $0.7 |
| Output / 1M | $2.20 |
| Cache read / 1M | $0.13 |
| Cache write / 1M | — |
| 1M in + 1M out | $2.90 |
| Takes | text |
| Returns | text |
| Tools | yes |
| Reasoning | optional · xhigh, high |
| Open weights | yes |
| Released | 2026-06-16 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | z-ai/glm-5.2:batch |
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.