Basic Usage

The OpenAI Responses API supports both simple string inputs and structured message arrays for generating text responses.

POST https://llm.siraya.ai/v1/responses

PythoncURL

import requests

response = requests.post(
    "https://llm.siraya.ai/v1/responses",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer <API_KEY>",
    },
    json={
        "model": "deepseek-v4-flash",
        "input": "Write a poem about the ocean.",
    }
)

print(response.json())

curl https://llm.siraya.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
    "model": "gpt-5.4",
    "input": "Hello!"
  }'

Example Response

{
  "id": "resp_J1alkT99rccXEbhfaYO4...",
  "object": "response",
  "created_at": 1780047388,
  "status": "completed",
  "error": null,
  "incomplete_details":null,
  "instructions":null,
  "max_output_tokens":null,
  "model": "gpt-5.4",
  "output": [
    {
      "id": "msg_07b05c2006fd78f0006a1...",
      "type": "message",
      "status":"completed",
      "content":[
        {
          "type":"output_text",
          "annotations":[],
          "logprobs":[],
          "text": "Hello! How can I help?"
        }
      ],
      "phase":"final_answer",
      "role":"assistant"
    }
  ],
  "usage": {
    "input_tokens": 8,
    "output_tokens": 10,
    "total_tokens": 18
  }
  "usage": {
    "input_tokens": 8,
    "output_tokens": 11,
    "total_tokens": 19,
    "input_tokens_details": { "cached_tokens":0 },
    "output_tokens_details":{ "reasoning_tokens":0}
  },
  "temperature":1,
  "top_p":0.98,
  "tool_choice":"auto",
  "tools":[],
  "metadata":{}
}