Skip to main content
Set "stream": true on a chat completions request to receive the response incrementally as Server-Sent Events (SSE), instead of waiting for the full completion. This is ideal for chat UIs where you want to render tokens as they arrive.

​
Example

from openai import OpenAI

client = OpenAI(base_url="https://api.deepshi.ai/v1", api_key="sk-bf-...")

stream = client.chat.completions.create(
    model="deepshi-3.0",
    messages=[{"role": "user", "content": "Write a haiku about the sea."}],
    stream=True,
)

for chunk in stream:
    delta = chunk.choices[0].delta.content
    if delta:
        print(delta, end="", flush=True)

​
The stream format

Each event is a data: line containing a partial chunk. Tokens arrive in choices[0].delta.content. The stream ends with a data: [DONE] sentinel: 
data: {"choices":[{"delta":{"content":"Wide"}}]}

data: {"choices":[{"delta":{"content":" blue"}}]}

data: [DONE]
Streaming works the same way for tool calls. The arguments arrive incrementally in delta.tool_calls. Accumulate them until finish_reason is tool_calls.