GLM 5.2
GLM 5.2 is a large language model made by Z.ai, added to the catalog on 16 Jun 2026. It has a context window of 1,048,576 tokens and costs $0.62 per 1M input tokens and $2.42 per 1M output tokens. It accepts text and produces text. Typical uses: reasoning over extensive text context, project-level software engineering and long-horizon agent workflows.
Price checked ยท source: OpenRouter
What GLM 5.2 is
Z.ai GLM 5.2 is a text-in, text-out reasoning model from Z.ai. It accepts text and produces text, with a context window of 1,048,576 tokens and a maximum output of 943,718 tokens. This capacity allows a request to include substantial source material or extended conversational context while leaving room for a large generated response. The catalog describes it as suited to long-horizon agent workflows and project-level software engineering, indicating a focus on tasks that involve sustained reasoning across a broader body of work rather than only short exchanges.
The model supports reasoning, tools, structured outputs, and response-format controls. These capabilities let applications provide tools as part of a workflow and request outputs in a defined structure or response format. Its text-only input and output make it appropriate where the material and result are expressed in text; the listed facts do not specify image, audio, or other non-text modalities. The large context window can accommodate lengthy specifications, code-related discussion, or project notes in a single context, though the catalog does not state how it performs on any particular task.
Its stated capabilities suit workflows involving text-based reasoning over extensive context, project-level software engineering, tool use, or generating text in a requested format. The catalog does not provide further details about particular programming languages, tools, or output schemas.
Key features
- Accepts text and produces text
- Has a 1,048,576-token context window
- Supports reasoning and tools
- Supports structured outputs and response-format controls
Typical uses
- Reasoning over extensive text context
- Project-level software engineering
- Long-horizon agent workflows
- Generating structured text
GLM 5.2 pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.62 | $0.322 |
| Output, per 1M tokens | $2.42 | $0.989 |
| Cached input read, per 1M tokens | $0.14 | $0.109 |
| Variant | Model id |
|---|---|
| Batch | z-ai/glm-5.2:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 16 Jun 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0010 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.017 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.023 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.097 |
GLM 5.2 specifications
| Model id | z-ai/glm-5.2 |
|---|---|
| Version | glm-5.2-20260616 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 16 Jun 2026 |
| Input types | text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for GLM 5.2 yet.
Compare GLM 5.2
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.