POST /paas/v4/chat/completions
Changed onCreate a chat completion model that generates AI replies for given conversation messages. It supports multimodal inputs (text, images, audio, video, file), offers configurable parameters (like temperature, max tokens, tool use), and supports both streaming and non-streaming output modes.
Request
- Base URLhttps://api.z.ai/api
- URLhttps://api.z.ai/api/paas/v4/chat/completions
- AuthHTTP bearer
Headers
Config desired response language for HTTP requests.
Request body
Example request
{
"model": "glm-5.3",
"messages": [
{
"content": "What opportunities and challenges will the Chinese large model industry face in 2025?"
}
],
"do_sample": true,
"thinking": {
"clear_thinking": true
},
"reasoning_effort": "max",
"temperature": 1,
"top_p": 0.95,
"max_tokens": 1024
}Response
Processing successful
Example response
{
"choices": [
{
"message": {
"role": "assistant"
}
}
]
}Changes
- info
added the new
glm-5.3-flashx-legalenum value to the request property/
- info
- breaking
removed the enum value
autoglm-phone-multilingualof the request property/ - breaking
removed the enum value
glm-4-32b-0414-128kof the request property/ - breaking
removed the enum value
glm-4.5of the request property/ - breaking
removed the enum value
glm-4.5-airof the request property/ - breaking
removed the enum value
glm-4.5-airxof the request property/ - breaking
removed the enum value
glm-4.5-flashof the request property/ - breaking
removed the enum value
glm-4.5-xof the request property/ - breaking
removed the enum value
glm-4.5vof the request property/ - breaking
removed the enum value
glm-4.6vof the request property/ - breaking
removed the enum value
glm-4.6v-flashof the request property/ - breaking
removed the enum value
glm-4.6v-flashxof the request property/ - breaking
removed the enum value
glm-4.7-flashof the request property/ - breaking
removed the enum value
glm-4.7-flashxof the request property/ - warning
removed the optional property
///from the response with the status
- breaking