Skip to content

Basic Usage

The OpenAI Responses API supports both simple string inputs and structured message arrays for chat-based interactions.

Endpoint

POST https://llm.siraya.pro/v1/chat/completions

Input Formats

1. Simple String Input

For quick queries, you can send a simple text prompt.

2. Structured Message Input

The recommended format for multi-turn conversations and system instructions.

{
  "model": "gpt-4o",
  "messages": [
    {"role": "system", "content": "You are a helpful travel assistant."},
    {"role": "user", "content": "Suggest a 3-day trip to Tokyo."}
  ]
}

Features

  • Stateless Execution: Each request is self-contained.
  • Multimodal Content: Support for images and documents in message content (where supported by the model).
  • Streaming: Real-time response generation using Server-Sent Events (SSE).

Example: Streaming Response

from openai import OpenAI

client = OpenAI(
    base_url="https://llm.siraya.pro/v1",
    api_key="<API_KEY>"
)

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a poem about the ocean."}],
    stream=True
)

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

curl https://llm.siraya.pro/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'