Zhipu

GLM 5.2

glm-5.2

View docs

Text generation for writing, questions and summaries. Try the verified short-copy example.

Pricing: Input 0.833334 · Output 2.916669 USD / 1M tokens
Output: Chat
Added to catalog: Oct 28, 2026

Input

Examples

Your message*

Enter a message or import TXT / Markdown text. Available attachment formats are shown below.

Default: Chinese cafe copy example

Response token limit

Default: 4096

Estimate the cost first. Generation starts only after confirmation.

OutputFill example

**Orux Café 温暖开业！我们备好了咖啡、灯光与靠窗的座位，欢迎邻居们带上心爱的书，把这里读成自己的书房。** （约52字）如需更简洁的版本，也可以用：「亲爱的邻居，Orux Café 开门啦！带上你正在读的那本书来坐坐吧，咖啡已经煮好了。」

README

Text generation for writing, questions and summaries. Try the verified short-copy example.

Model capabilities

Input modalities: Text
Output modalities: Text
Context caching: Supported
Tool calling: Not confirmed
Streaming: Not confirmed
Batch inference: Not supported

API protocol support

Chat Completions: Supported
Responses: Not supported
Gemini: Not supported
Anthropic: Not supported

Model limits

Context length: Not confirmed
Maximum output: Not confirmed

Writing, questions and summaries

The Chinese cafe opening copy is a real response from this model. Edit its prompt or select a summary or coding prompt. The latter examples provide reusable inputs without fabricated outputs.

Pricing and usage

Input, output and cache usage are billed separately according to the price table. Context and time-based tiers apply where listed; peak and off-peak times use UTC+8. Review the estimate before calling; final cost depends on returned usage.

Text requests and responses have been verified. Refer to the capabilities section for other input types and tools.

Parameters

Fields accepted in the request body for this model.

messagesmessages

Required

Enter a message or import TXT / Markdown text. Available attachment formats are shown below.

max_tokensinteger

Optional

Range: ≥ 1Default: 4096

Advanced

temperaturenumber

Optional

Adjust response randomness. Tune either temperature or top_p.

Range: 0 – 2

top_pnumber

Optional

Range: 0 – 1

response_formatobject

Optional

For JSON output, describe the expected JSON structure in your prompt.

Values: Text / JSON object

toolsobject

Optional

tool_choiceobject

Optional

Select a function, for example {"type":"function","function":{"name":"lookup"}}.

Pricing

USD / 1M tokens

Standard

Input0.833334

Output2.916669

Cache read0.2083335

Bill actual quantity

Minimum per call: 0 USD · Rounding is applied once to the total cost

Only listed usage types are supported for automatic billing

Pricing follows the selected specifications

Prices are billed per unit consumed with no monthly minimum. See billing guide for USD estimates and actual usage charges.

Code

View docs →

POST https://orux.top/api/v1/chat/completions

Code examples

Request body

curl 'https://orux.top/api/v1/chat/completions' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "messages": [
    {
      "role": "user",
      "content": "为一家名为 Orux Café 的社区咖啡店写两句温暖的开业文案，包含欢迎邻居带书来阅读。不超过80字。"
    }
  ],
  "max_tokens": 4096,
  "model": "glm-5.2"
}'

Swipe horizontally to view the full content

Code examples

Response examples

{
  "id": "chatcmpl-...",
  "choices": [
    { "index": 0, "message": { "role": "assistant", "content": "Hello! How can I help you today?" } }
  ],
  "usage": { "prompt_tokens": 12, "completion_tokens": 9, "total_tokens": 21 }
}

Swipe horizontally to view the full content

Frequently asked questions

About GLM 5.2 pricing, capabilities and API access on Orux AI.

Does selecting an example incur a charge?

No. Selecting an example only fills the form. A model call starts after you confirm generation or send a request.

What is GLM 5.2?

GLM 5.2: Text generation for writing, questions and summaries. Try the verified short-copy example.

How much does GLM 5.2 cost on Orux AI?

Input: 166.6668 Credits; output: 583.3338 Credits, per 1M tokens. See the pricing section on this page for GLM 5.2 pricing and applicable conditions. Charges depend on the selected parameters and recorded usage.

What inputs and outputs does GLM 5.2 support?

GLM 5.2 accepts Text and returns Text.

Where can I access the GLM 5.2 API?

Create an Orux AI API key and send an authenticated POST request to https://orux.top/api/v1/chat/completions, using glm-5.2 as the model identifier. Try the playground on this page and use the API example for the exact request format.