Streaming Responses

Chat Completions streaming request

Set stream: true to receive incremental events in SSE format.

curl -N "${BASE_URL}/v1/chat/completions" \
  -H "Authorization: Bearer ${API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
      {
        "role": "user",
        "content": "Output three troubleshooting suggestions in sequence"
      }
    ],
    "stream": true,
    "stream_options": {
      "include_usage": true
    }
  }'

SSE event shape

data: {"id":"chatcmpl_xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":"First"}}]}

data: {"id":"chatcmpl_xxx","object":"chat.completion.chunk","choices":[{"delta":{"content":" suggestion"}}]}

data: {"id":"chatcmpl_xxx","object":"chat.completion.chunk","choices":[{"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":20,"completion_tokens":30,"total_tokens":50}}

data: [DONE]

Client handling suggestions

• Parse each SSE data: line independently.
• Close the stream after receiving [DONE].
• Pass stream_options.include_usage=true if the client needs usage details.
• If the client disconnects, the request may still complete and generate usage or billing.

Python SDK example

stream = client.chat.completions.create(
    model="gpt-4.1",
    messages=[{"role": "user", "content": "Output three troubleshooting suggestions in sequence"}],
    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="")