ToRouter DocsGateway
Streaming responses (SSE)
Stream tokens incrementally over Server-Sent Events for OpenAI, Anthropic and Gemini protocols.
All three protocols stream via Server-Sent Events. Set the appropriate flag and consume events as they arrive.
How to enable
| Protocol | Flag |
|---|---|
| OpenAI Chat / Responses | "stream": true in the JSON body |
| Anthropic | "stream": true in the JSON body |
| Gemini | use :streamGenerateContent + ?alt=sse |
SSE format
Events arrive as data: lines separated by blank lines. The OpenAI stream terminates with data: [DONE]. Anthropic and Gemini use protocol-specific terminator events.
data: {"id":"...","object":"chat.completion.chunk","choices":[{"delta":{"content":"He"}}]}
data: {"id":"...","object":"chat.completion.chunk","choices":[{"delta":{"content":"llo"}}]}
data: [DONE]Python
from openai import OpenAI
client = OpenAI(api_key="sk-***", base_url="https://portal.torouter.ai/v1")
stream = client.chat.completions.create(
model="gpt-5",
messages=[{"role": "user", "content": "Count to 5"}],
stream=True,
)
for chunk in stream:
delta = chunk.choices[0].delta.content
if delta:
print(delta, end="", flush=True)from anthropic import Anthropic
client = Anthropic(api_key="sk-***", base_url="https://portal.torouter.ai")
with client.messages.stream(
model="claude-opus-4-7",
max_tokens=256,
messages=[{"role": "user", "content": "Count to 5"}],
) as stream:
for text in stream.text_stream:
print(text, end="", flush=True)Node.js
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "sk-***",
baseURL: "https://portal.torouter.ai/v1",
});
const stream = await client.chat.completions.create({
model: "gpt-5",
messages: [{ role: "user", content: "Count to 5" }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}Reasoning models (e.g. *-thinking, o1, o3) emit reasoning content before the answer. Where supported, the OpenAI SDK surfaces this via delta.reasoning_content.