Streaming

Terima respons secara real-time menggunakan Server-Sent Events (SSE).

Endpoint

POSThttps://api.sribuai.my.id/v1/chat/completions

Cara Mengaktifkan

Tambahkan stream: true pada request body. Format respons menggunakan SSE — setiap chunk dikirim sebagai data: {...}.

Contoh Streaming

from openai import OpenAI

client = OpenAI(
    base_url="https://api.sribuai.my.id/v1",
    api_key="sk-sri-xxxxx"
)

stream = client.chat.completions.create(
    model="claude-sonnet-4-5",
    messages=[{"role": "user", "content": "Tulis puisi tentang AI"}],
    stream=True,
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="", flush=True)

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.sribuai.my.id/v1',
  apiKey: 'sk-sri-xxxxx',
})

const stream = await client.chat.completions.create({
  model: 'claude-sonnet-4-5',
  messages: [{ role: 'user', content: 'Tulis puisi tentang AI' }],
  stream: true,
})

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

curl https://api.sribuai.my.id/v1/chat/completions \
  -H "Authorization: Bearer sk-sri-xxxxx" \
  -H "Content-Type: application/json" \
  --no-buffer \
  -d '{
    "model": "claude-sonnet-4-5",
    "messages": [{"role": "user", "content": "Tulis puisi tentang AI"}],
    "stream": true
  }'

Format Chunk

Setiap chunk SSE memiliki format:

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

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

data: [DONE]

End of Stream

Stream berakhir saat menerima data: [DONE].

← Chat Completions Rate Limits →