# GLM-5.2

`dashscope/glm-5.2` · Z.ai · text

GLM-5.2 can work through long engineering tasks using source text and results from tools. A million-token context keeps earlier decisions within reach.

[Model page](https://sociaro.com/models/dashscope/glm-5.2) · [JSON](https://sociaro.com/models/dashscope/glm-5.2.json) · [Model pricing](https://sociaro.com/pricing?model=dashscope%2Fglm-5.2) · [Documentation](https://docs.sociaro.com/models/dashscope-glm-5-2/)

## Use cases

- Plan a refactor across several services
- Revise a debugging plan after reading test output

## Technical details

- API model ID — dashscope/glm-5.2
- Provider — Z.ai
- Modality — Text
- Input — Chat messages
- Output — Text
- Endpoint — POST /v1/chat/completions
- API constraints — While thinking is on, tool_choice cannot force a tool: use auto or none.

## Request parameters

- `messages`
- `temperature`
- `top_p`
- `max_tokens`
- `max_completion_tokens`
- `stream`
- `stream_options`
- `tools`
- `tool_choice`
- `parallel_tool_calls`
- `enable_thinking`
- `thinking_budget`
- `seed`
- `stop`
- `presence_penalty`
- `top_k`
- `repetition_penalty`

## Pricing

Rates in USD. Catalogue timestamp 2026-11-21T02:23:44Z.

- USD 1.68 per 1M input tokens · active
- USD 5.28 per 1M output tokens · active
- USD 0.336 per 1M cached input tokens · active
