Raon
Docs

Streaming

Receive the answer as server-sent events while it is written.

Set stream to true on any of the three APIs to receive server-sent events as the answer is written. The Python examples continue from the client set up on Chat Completions or Messages.

stream = client.chat.completions.create(
    model="raon-1-mini-preview",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
  • On Chat Completions, stream_options.include_usage adds token usage in a final chunk.
  • With curl, add -N so the output is not buffered.