glm-5.3

Unified endpoint for Zhipu GLM series chat models exposed through the baze platform.

Supported model: glm-5.3.

Documented fields: model, messages, stream, thinking, temperature, top_p, max_tokens, stop, tools, tool_choice.

POST /v1/chat/completions

cURL

text_chat

curl --request POST \
  --url https://baze-api.powerbuyin.top/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "glm-5.3",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise and professional assistant."
    },
    {
      "role": "user",
      "content": "Describe vector databases in three sentences."
    }
  ],
  "temperature": 0.7,
  "max_tokens": 1024
}
'

200

{
  "id": "chatcmpl_zhipu_123",
  "object": "chat.completion",
  "created": 1775174400,
  "model": "glm-5.3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "A vector database is a data system designed to store and retrieve vector representations, commonly used for semantic search, recommendations, and RAG.",
        "reasoning_content": "Start with the definition, then add typical use cases."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 31,
    "total_tokens": 73,
    "prompt_tokens_details": {
      "cached_tokens": 0
    }
  }
}

Authorizations

Authorization · string · header · required

Pass Authorization: Bearer <token> in the request header.

Body

application/json

Zhipu Chat Completions request body.

model · enum<string> · required

Model name. Supported model: glm-5.3.

Available options: glm-5.3

Example:

"glm-5.3"

messages · object[] · required

Message list. The request must contain at least one message that is not system or assistant; sending only system or only assistant messages will be rejected by the upstream provider.

Minimum array length: 1

Show child attributes

stream · boolean · default: true

Whether to enable streaming output. When true, the response is returned as text/event-stream.

thinking · object

Thinking mode configuration. Applicable to models that support the thinking parameter.

Show child attributes

reasoning_effort · enum<string> · default: max

Controls the model's reasoning intensity. Takes effect when thinking is enabled. Defaults to max. Only supported by GLM-5.2 and above models. For GLM-5.3 / GLM-5.3-FLASH models, only low / high / max tiers are supported. For GLM-5.2 models, passing none or minimal causes the model to skip thinking; passing low / medium maps to high; passing xhigh maps to max.

Available options: max, xhigh, high, medium, low, minimal, none

temperature · number · default: 1

Sampling temperature, range [0, 1].

Required range: 0 <= x <= 1

top_p · number · default: 0.95

Nucleus sampling probability threshold, range [0.01, 1].

Required range: 0.01 <= x <= 1

max_tokens · integer

Maximum number of output tokens.

Required range: 1 <= x <= 131072

stop · string[]

Stop sequence list. Currently only a single stop sequence is supported.

Maximum array length: 1

tools · object[]

Tool definition list. Currently only function type tools are supported.

Maximum array length: 128

Show child attributes

tool_choice · enum<string> · default: auto

Tool selection strategy. The Zhipu API currently only exposes auto.

Available options: auto

Response

200

application/json

Success. Non-streaming mode returns JSON; streaming mode returns an SSE event stream.

Non-streaming Chat Completions response.

id · string

Response ID.

object · string

Object type.

Example:

"chat.completion"

created · integer<int64>

Unix timestamp (seconds).

model · string

The model name actually used.

choices · object[]

Candidate results returned by the model.

Show child attributes

usage · object

Token usage statistics.

Show child attributes