Web Search API

The Web Search API provides real-time internet information retrieval, enabling AI models to access the latest web content for more accurate and up-to-date responses. The API is compatible with the OpenAI Chat Completions format for seamless integration.

Try it Online

Test in Playground ↗ · View Models ↗

Quick Start

curl -X POST https://open.dieyuyun.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "web-search",
    "messages": [
      {"role": "user", "content": "What are the latest developments in AI?"}
    ]
  }'

Endpoint

Property	Value
Method	POST
Path	/v1/chat/completions
Base URL	https://open.dieyuyun.com
Protocol	OpenAI-compatible

Authentication

All requests must include your API key in the header:

Authorization: Bearer YOUR_API_KEY

Request Fields

Field	Type	Required	Default	Description
model	string	Yes	—	Model identifier, always web-search
messages	array	Yes	—	Message list, compatible with OpenAI message format
stream	boolean	No	false	Enable streaming output
max_tokens	integer	No	2048	Maximum output tokens

Message Roles

Role	Description
system	System prompt (optional)
user	User message
assistant	Assistant reply (for multi-turn scenarios)

Request Examples

cURL

curl -X POST https://open.dieyuyun.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "web-search",
    "messages": [
      {"role": "user", "content": "What are the latest breakthroughs in AI research?"}
    ],
    "max_tokens": 4096
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://open.dieyuyun.com/v1"
)

response = client.chat.completions.create(
    model="web-search",
    messages=[
        {"role": "user", "content": "What are the latest breakthroughs in AI research?"}
    ],
    max_tokens=4096
)

print(response.choices[0].message.content)

Node.js

import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://open.dieyuyun.com/v1',
})

const response = await client.chat.completions.create({
  model: 'web-search',
  messages: [{ role: 'user', content: 'What are the latest breakthroughs in AI research?' }],
  max_tokens: 4096,
})

console.log(response.choices[0].message.content)

Response Format

Standard Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1705312200,
  "model": "web-search",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Based on the latest internet information, here are the recent important AI research breakthroughs:\n\n1. ...\n\n**Sources:**\n- [Source 1](https://example.com/article1)\n- [Source 2](https://example.com/article2)"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 580,
    "total_tokens": 605
  }
}

Streaming Output

Set stream: true to receive responses in Server-Sent Events (SSE) format:

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Based"},"finish_reason":null}]}

data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":" on"},"finish_reason":null}]}

data: [DONE]

Use Cases

Use Case	Description
Real-time information	Retrieve news, stock market data, weather, and other live info
Knowledge gap filling	Supplement model knowledge beyond its training cutoff date
Fact checking	Verify specific facts, data points, or citations
Multi-turn search dialog	Continuously search and follow up on topics across a conversation

Best Practices

1. Ask specific questions: Precise queries yield more accurate search results — avoid overly broad questions
2. Multi-turn follow-up: Use conversational turns to drill deeper, focusing each query on a specific aspect
3. Use system prompts: Set the response style via the system message, e.g., "Answer concisely and include sources"
4. Enable streaming: For user-facing applications (e.g., chatbots), enable stream: true to reduce time-to-first-token
5. Control token usage: Set appropriate max_tokens to avoid overly long responses

Pricing

Web search is billed per request at ¥0.02 per call, regardless of response length. See Pricing for details.

Rate Limits

Limit	Value
Requests/min	30 RPM
Concurrent	5

Need higher limits? Submit a ticket in the Console.