Drise
Api reference

Streaming responses

Stream GLM 5.2 chat completions with server-sent events.

Set stream: true in the chat completions request body. Drise returns a standard OpenAI-style SSE stream of chat.completion.chunk events.

Example request

curl https://platform.drise.ai/v1/chat/completions \
  -H "Authorization: Bearer $DRISE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "drise-glm-5.2",
    "stream": true,
    "messages": [{"role": "user", "content": "stream me a haiku about latency"}]
  }'

Event shape

data: {"id":"...","object":"chat.completion.chunk","choices":[{"delta":{"content":"Fast"},"index":0}]}

data: [DONE]

The stream ends with a data: [DONE] line, same as OpenAI. Any OpenAI-compatible client handles this out of the box.

On this page