POST
/
v1
/
chat
/
completions
Web Search
curl --request POST \
  --url https://api.example.com/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "temperature": 123,
  "max_tokens": 123,
  "stream": true,
  "web_search": true
}
'
{
  "id": "<string>",
  "object": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {}
  ],
  "usage": {}
}
Chat completions interface enhanced with Web search functionality for real-time web information.

​
Overview

The Web Search interface allows AI models to access real-time web information when generating responses. This is particularly useful for queries that require up-to-date information.

​
Authentication

All requests require a Bearer token in the Authorization header: 
Authorization: Bearer YOUR_API_KEY

​
Request Parameters

​
model
string
required
ID of the model to use. Models supporting Web search include GPT models with search capabilities.
​
messages
array
required
A list of messages comprising the conversation.
​
temperature
number
default:"1"
Sampling temperature between 0 and 2. Higher values make output more random, lower values make it more focused.
​
max_tokens
integer
Maximum number of tokens to generate.
​
stream
boolean
default:"false"
Whether to stream responses.
​
web_search
boolean
default:"true"
Whether to enable Web search functionality.

​
Request Example

curl -X POST https://api.example.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4-web",
    "messages": [
      {"role": "user", "content": "What are today news headlines?"}
    ],
    "web_search": true,
    "temperature": 0.7
  }'

​
Response Example

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4-web",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Based on the latest web search results, today's main news headlines include..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 150,
    "total_tokens": 165
  }
}

​
Response Fields

​
id
string
Unique identifier for the completion.
​
object
string
Object type, which is chat.completion.
​
created
integer
Unix timestamp of when the completion was created.
​
model
string
The model used.
​
choices
array
List of completion choices.
​
usage
object
Usage statistics for the request.

​
Parameters

ParameterTypeRequiredDefaultDescription
modelstringYes-ID of the model to use
messagesarrayYes-List of messages in the conversation
temperaturenumberNo1Sampling temperature (0-2)
max_tokensintegerNo-Maximum tokens to generate
streambooleanNofalseEnable streaming responses
web_searchbooleanNotrueEnable Web search