Streaming

stream = client.chat.completions.create(
    model="deepseek-v4",
    messages=[{"role": "user", "content": "Write a short intro"}],
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

A few details

• ·usage arrives only in the final chunk, so pass stream_options to receive it.
• ·If upstream drops the stream, the gateway will not silently fill in the gap — it ends with an error event; retry on the client side.
• ·Time to first token is measured when the edge node receives the first chunk, and is visible per request in the usage logs.