Streaming

Stream tokens over Server-Sent Events. Use it when users benefit from seeing output as it is generated, such as chat, coding, and long-form responses.

Examples

Python

from openai import OpenAI

client = OpenAI(base_url="https://test.sealink.io/v1", api_key="<your-sealink-key>")

stream = client.chat.completions.create(
    model="qwen3-max",
    messages=[{"role": "user", "content": "Stream a 200-word reply."}],
    stream=True,
)

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

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://test.sealink.io/v1",
  apiKey: process.env.SEALINK_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "qwen3-max",
  messages: [{ role: "user", content: "Stream a 200-word reply." }],
  stream: true,
});

for await (const chunk of stream) {
  const delta = chunk.choices[0]?.delta?.content;
  if (delta) process.stdout.write(delta);
}

cURL (-N keeps stream open)

curl https://test.sealink.io/v1/chat/completions \
  -H "Authorization: Bearer $SEALINK_API_KEY" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "qwen3-max",
    "messages": [{"role":"user","content":"Stream please"}],
    "stream": true
  }'

When to enable streaming

Chat / customer-support UIs where users need visible progress
Code generation and code explanation
Longer responses or tasks that need immediate feedback

When not to stream

When you need to parse complete JSON or structured output
Very short background responses where streaming adds little value
Background batch jobs where nobody watches the output

Common pitfalls

Proxies / nginx / Cloudflare buffer SSE by default. SeaLink disables buffering server-side but verify your stack forwards correctly.
Forgetting to close the stream leaks connections — use try/finally or an async iterator that auto-closes.
Usage is finalized at stream end. OpenAI SDK emits usage on the last frame (set stream_options={"include_usage": true}).