Streaming

Receive AI responses token-by-token in real time using server-sent events.

Streaming lets you display AI responses as they’re generated, instead of waiting for the full response. This creates a much better user experience for chat interfaces.

ShuttleAI uses Server-Sent Events (SSE) — the same streaming format as OpenAI.

Basic streaming

Set stream: true in your request to enable streaming:

Python

from openai import OpenAI

client = OpenAI(
    api_key="shuttle-xxx",
    base_url="https://api.shuttleai.com/v1"
)

stream = client.chat.completions.create(
    model="shuttleai/auto",
    messages=[{"role": "user", "content": "Write a short poem about AI."}],
    stream=True
)

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

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "shuttle-xxx",
  baseURL: "https://api.shuttleai.com/v1",
});

const stream = await client.chat.completions.create({
  model: "shuttleai/auto",
  messages: [{ role: "user", content: "Write a short poem about AI." }],
  stream: true,
});

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

curl https://api.shuttleai.com/v1/chat/completions \
  -H "Authorization: Bearer shuttle-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "shuttleai/auto",
    "messages": [{"role": "user", "content": "Write a short poem about AI."}],
    "stream": true
  }'

Async streaming (Python)

For async applications, use the async client:

import asyncio
from openai import AsyncOpenAI

client = AsyncOpenAI(
    api_key="shuttle-xxx",
    base_url="https://api.shuttleai.com/v1"
)

async def main():
    stream = await client.chat.completions.create(
        model="shuttleai/auto",
        messages=[{"role": "user", "content": "Explain quantum computing."}],
        stream=True
    )

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

asyncio.run(main())

Stream with usage stats

To receive token usage statistics with your stream, enable stream_options:

stream = client.chat.completions.create(
    model="shuttleai/auto",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
    stream_options={"include_usage": True}
)

The final chunk in the stream will include a usage object with prompt_tokens, completion_tokens, and total_tokens.

SSE format

Each streamed chunk is a JSON object sent as an SSE event:

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":" world"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: [DONE]

The stream ends with data: [DONE].