# Prompts for GLM: constraints first, no inflated roles

> How to prompt GLM-5.3 and GLM-5.3 Flash from Z.ai (Zhipu AI): always-on reasoning, key constraints early, roles that serve the task and JSON with explicit fields.

Source: Promptea — https://www.promptea.me/en/models/glm · Language: English · Last updated: 2026-11-14

## Quick tips

- Zhipu's prompt guide says to give the important constraints you already know as early as possible, not as an afterthought at the end.
- A role should serve the task: skip titles like 'world-class expert'. A role does not replace the task description, the source material or the criteria to check the answer.
- Use tags or delimiters named after what they contain, consistently, so the model separates the rules it must follow from the material it must process.
- GLM-5.3 always reasons and takes text only; choose reasoning_effort (low, high or max). GLM-5.3 Flash also reads images and video.

## Current models Promptea supports

Capabilities come from the provider’s official documentation; each entry shows the date it was last verified.

### GLM-5.3 (default)

Z.ai's (Zhipu AI) flagship, Aug 2026: 1M context, text only, always reasons. Strong at coding and tool use.

- Context window: 1M tokens · max output: 131K
- Input: text · output: text
- Latency: slower (deliberate) · structured output: yes · tool use: yes · native search: no
- Strengths: reasoning, coding, long context
- How to prompt it: Reasoning cannot be turned off: pick reasoning_effort low, high or max (default max) for the task. Text input only. For JSON, define the structure and allowed values in the prompt.
- Verified: 2026-11-14 — [source](https://docs.z.ai/guides/llm/glm-5.3)

### GLM-5.3 Flash

Cheaper, natively multimodal GLM (video, image, text and file input), Aug 2026: 1M context and always-on reasoning.

- Context window: 1M tokens · max output: 131K
- Input: text, image, video · output: text
- Latency: balanced · structured output: no · tool use: yes · native search: no
- Strengths: speed, multimodal, long context
- How to prompt it: Always reasons; Z.ai recommends temperature 1 and top_p 0.95. Separate the file or image from the instructions and ask for the exact output format.
- Verified: 2026-11-14 — [source](https://docs.z.ai/guides/vlm/glm-5.3-flash)

## Templates

### Constraints-first task

```text
Constraints (apply to everything below):
- Audience: [who]
- Length: [limit]
- Must not: [what to avoid]

Task: [what to produce]

<source>
[material to work on]
</source>

Done when: [how to check the answer]
```

[Open in Promptea](https://www.promptea.me/en/analyzer?prompt=Constraints+%28apply+to+everything+below%29%3A%0A-+Audience%3A+%5Bwho%5D%0A-+Length%3A+%5Blimit%5D%0A-+Must+not%3A+%5Bwhat+to+avoid%5D%0A%0ATask%3A+%5Bwhat+to+produce%5D%0A%0A%3Csource%3E%0A%5Bmaterial+to+work+on%5D%0A%3C%2Fsource%3E%0A%0ADone+when%3A+%5Bhow+to+check+the+answer%5D&purpose=text&target=glm)

## Frequently asked questions

### Can I turn GLM-5.3's reasoning off?

No. Z.ai's docs say disabling reasoning is no longer supported; set reasoning_effort to low for quick tasks instead (the default is max).

### Is asking for 'JSON' enough?

No. Zhipu's guide asks you to define the structure, what each field means and which values it allows, and to keep validating the result in your application.
