Streaming Respons

Streaming pada endpoint /v1/chat/completions memungkinkan aplikasi Anda menampilkan token teks seketika saat dihasilkan oleh model AI, memangkas perceived latency untuk antarmuka chat dan CLI.

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.neosantara.xyz/v1",
    api_key=os.environ["NEOSANTARA_API_KEY"]
)

stream = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Tuliskan panduan arsitektur microservices."}],
    stream=True
)

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

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.neosantara.xyz/v1",
  apiKey: process.env.NEOSANTARA_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [{ role: "user", content: "Jelaskan prinsip SOLID secara ringkas." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}
console.log();

curl -N -X POST https://api.neosantara.xyz/v1/chat/completions \
  -H "Authorization: Bearer $NEOSANTARA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash",
    "messages": [{"role": "user", "content": "Halo"}],
    "stream": true
  }'

Format Event Stream

Setiap chunk dikirim sebagai event SSE dengan format data: <JSON>:

data: {"id":"chatcmpl-abc","object":"chat.completion.chunk","created":1741764000,"model":"deepseek-v4.1-flash","choices":[{"index":0,"delta":{"content":"Halo"},"finish_reason":null}]}

Ketika generasi token selesai, gateway mengirimkan sinyal penutup:

data: [DONE]

Melacak Penggunaan Token saat Streaming

Sertakan parameter stream_options untuk menerima total token yang digunakan pada chunk terakhir:

stream = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Halo"}],
    stream=True,
    stream_options={"include_usage": True}
)

for chunk in stream:
    if chunk.usage:
        print(f"\nTotal token: {chunk.usage.total_tokens}")
    else:
        print(chunk.choices[0].delta.content or "", end="", flush=True)

Langkah Selanjutnya

Kebutuhan	Panduan
Panggil Fungsi Eksternal	Function Calling
Output JSON Tervalidasi	Structured Outputs
Ekstraksi Pemikiran Model	Penalaran Model

Topik terkait

Chat Completions Streaming Respons Anthropic Penalaran (Reasoning)Batas Rate & Throughput

⌘I

Memulai

Pengantar & Model

Protokol Kompatibilitas

Modalitas Khusus

Operasional Gateway

Format Event Stream

Melacak Penggunaan Token saat Streaming

Langkah Selanjutnya

​Format Event Stream

​Melacak Penggunaan Token saat Streaming

​Langkah Selanjutnya

Format Event Stream

Melacak Penggunaan Token saat Streaming

Langkah Selanjutnya