Skip to main content

Chat Completions

The Chat Completions API provides a unified interface to call multiple models (such as OpenAI, Claude, DeepSeek, and others). Core parameters remain consistent; you usually only need to switch the model name.

Request​

POST /chat/completions

Request Body
{
  "model": "gpt-4.1",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Describe the key features of Qiyiguo AI in one sentence." }
  ],
  "temperature": 0.7
}

Response​

Response Example
{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1710000000,
  "model": "gpt-4.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Qiyiguo AI offers a unified API, supports multiple models, and covers scenarios such as chat, reasoning, coding, translation, and text processing with simple and reliable integration."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Best Practices​

  • Use the system message to define the assistant role for more consistent replies
  • Choose models based on cost, latency, and capability requirements
  • For long conversations, implement message truncation or summarization