Streaming · Laras Router Docs

Set "stream": true to receive the answer as it is generated. The response is a stream of Server-Sent Events (text/event-stream) in the OpenAI format: each event is a chat.completion.chunk, and the stream ends with data: [DONE].

Stream a response

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.larasrouter.com/v1",
    api_key=os.environ["LARAS_API_KEY"],
)

stream = client.chat.completions.create(
    model="deepseek-flash",
    messages=[{"role": "user", "content": "Write a haiku about Jakarta rain."}],
    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="", flush=True)
    if chunk.usage:
        print(f"\n\n{chunk.usage.total_tokens} tokens")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.larasrouter.com/v1",
  apiKey: process.env.LARAS_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "deepseek-flash",
  messages: [{ role: "user", content: "Write a haiku about Jakarta rain." }],
  stream: true,
  stream_options: { include_usage: true },
});

for await (const chunk of stream) {
  const text = chunk.choices[0]?.delta?.content;
  if (text) process.stdout.write(text);
  if (chunk.usage) console.log(`\n\n${chunk.usage.total_tokens} tokens`);
}

curl https://api.larasrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $LARAS_API_KEY" \
  -H "Content-Type: application/json" \
  --no-buffer \
  -d '{
    "model": "deepseek-flash",
    "messages": [{"role": "user", "content": "Write a haiku about Jakarta rain."}],
    "stream": true,
    "stream_options": {"include_usage": true}
  }'

What the stream looks like

text/event-stream

data: {"id":"chatcmpl-…","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant","content":""}}]}

data: {"id":"chatcmpl-…","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Grey sky"}}]}

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

data: {"id":"chatcmpl-…","object":"chat.completion.chunk","choices":[],"usage":{"prompt_tokens":16,"completion_tokens":42,"total_tokens":58,"prompt_cache_hit_tokens":0,"prompt_cache_miss_tokens":16}}

data: [DONE]

Reasoning arrives first, in delta.reasoning_content, before the answer's delta.content. See Reasoning content.
Tool calls arrive as delta.tool_calls fragments that you concatenate by index. See Tool calling.

Token usage

With stream_options.include_usage set to true, the last chunk before [DONE] carries the usage object and an empty choices array. Without it, you receive no usage chunk — your request is still metered and charged the same way, and you can see it in the console under Usage.

How a stream ends

Normally: a chunk with a finish_reason, then (if requested) the usage chunk, then data: [DONE]. We send [DONE] only after the request's usage has been recorded, so a stream you saw finish is a stream we billed exactly.
With an error mid-stream: if the provider fails after the stream has started, the stream ends with an error event in the usual envelope, for example data: {"error":{"message":"…","type":"api_error","code":"provider_unavailable","param":null}}. Treat a stream that ends without [DONE] as incomplete.
Errors before the stream starts — an invalid key, an empty wallet, a rate limit — are returned as a normal JSON error response with the matching HTTP status, not as a stream. See Errors & retries.