Web Search

Enable AI models to search the web for real-time information

Requesty supports native web search across major providers. Pass a single tool definition and Requesty translates it to the right provider format automatically.

Native web search providers: Vertex AI (Google), Azure OpenAI, OpenAI, Anthropic, xAI, Perplexity

Browse models with web search in the Requesty Console. Look for supports_web_search: true in the List Models response.

How It Works

Each provider implements web search differently. Requesty normalizes these differences behind a single tool definition that works across all three inference endpoints:

Endpoint	Format	Tool definition
/v1/chat/completions	OpenAI Chat Completions	"tools": [{ "type": "web_search" }]
/v1/responses	OpenAI Responses API	"tools": [{ "type": "web_search" }]
/v1/messages	Anthropic Messages	"tools": [{ "type": "web_search_20250305", "name": "web_search", "max_uses": 5 }]

We recommend using streaming ("stream": true) for all web search requests. Streaming delivers citations and content in real time, and avoids the extra latency of waiting for the full search to finish.

Usage

Chat Completions

POST /v1/chat/completions - Add { "type": "web_search" } to the tools array.

cURL

curl https://router.requesty.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "anthropic/claude-sonnet-4-20250514",
    "messages": [
      { "role": "user", "content": "What are the latest news in London today?" }
    ],
    "tools": [{ "type": "web_search" }],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.requesty.ai/v1",
)

stream = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-20250514",
    messages=[
        {"role": "user", "content": "What are the latest news in London today?"}
    ],
    tools=[{"type": "web_search"}],
    stream=True,
)

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

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_REQUESTY_API_KEY',
  baseURL: 'https://router.requesty.ai/v1',
});

const stream = await client.chat.completions.create({
  model: 'anthropic/claude-sonnet-4-20250514',
  messages: [
    { role: 'user', content: 'What are the latest news in London today?' }
  ],
  tools: [{ type: 'web_search' }],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}

Just change the model to switch providers:

# Vertex / Gemini
model="vertex/google/gemini-2.5-pro"

# xAI / Grok
model="xai/grok-3"

# Perplexity
model="perplexity/sonar-pro"

Response includes web_search metadata on streamed chunks with citation URLs and titles:

{
  "choices": [{
    "delta": {
      "content": "Based on the search results...",
      "web_search": {
        "content": [
          { "url": "https://example.com/news", "title": "London News" }
        ]
      }
    }
  }]
}

Responses API

POST /v1/responses - Add { "type": "web_search" } to the tools array.

cURL

curl https://router.requesty.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "openai-responses/gpt-4.1",
    "input": "What are the latest developments in artificial intelligence?",
    "tools": [{ "type": "web_search" }],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.requesty.ai/v1",
)

response = client.responses.create(
    model="openai-responses/gpt-4.1",
    input="What are the latest developments in artificial intelligence?",
    tools=[{"type": "web_search"}],
    stream=True,
)

for event in response:
    if hasattr(event, 'type') and event.type == 'response.completed':
        for item in event.response.output:
            if item.type == 'message':
                for content in item.content:
                    if content.type == 'output_text':
                        print(content.text)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_REQUESTY_API_KEY',
  baseURL: 'https://router.requesty.ai/v1',
});

const response = await client.responses.create({
  model: 'openai-responses/gpt-4.1',
  input: 'What are the latest developments in artificial intelligence?',
  tools: [{ type: 'web_search' }],
});

for (const item of response.output) {
  if (item.type === 'message') {
    for (const content of item.content) {
      if (content.type === 'output_text') {
        console.log(content.text);
      }
    }
  }
}

Response includes web_search_call items and url_citation annotations on text content:

{
  "output": [
    {
      "type": "web_search_call",
      "id": "ws_abc123",
      "status": "completed"
    },
    {
      "type": "message",
      "role": "assistant",
      "content": [{
        "type": "output_text",
        "text": "Recent AI developments include...",
        "annotations": [{
          "type": "url_citation",
          "url": "https://example.com/ai-news",
          "title": "AI News Today",
          "start_index": 0,
          "end_index": 35
        }]
      }]
    }
  ]
}

Messages API

POST /v1/messages - Uses Anthropic’s native web_search_20250305 tool type.

cURL

curl https://router.requesty.ai/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_REQUESTY_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "anthropic/claude-sonnet-4-20250514",
    "max_tokens": 4096,
    "messages": [
      { "role": "user", "content": "What are the latest developments in artificial intelligence?" }
    ],
    "tools": [{
      "type": "web_search_20250305",
      "name": "web_search",
      "max_uses": 5
    }],
    "stream": true
  }'

import anthropic

client = anthropic.Anthropic(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.requesty.ai",
)

with client.messages.stream(
    model="anthropic/claude-sonnet-4-20250514",
    max_tokens=4096,
    messages=[
        {"role": "user", "content": "What are the latest developments in artificial intelligence?"}
    ],
    tools=[{
        "type": "web_search_20250305",
        "name": "web_search",
        "max_uses": 5,
    }],
) as stream:
    response = stream.get_final_message()

for block in response.content:
    if block.type == "text":
        print(block.text)

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  apiKey: 'YOUR_REQUESTY_API_KEY',
  baseURL: 'https://router.requesty.ai',
});

const stream = client.messages.stream({
  model: 'anthropic/claude-sonnet-4-20250514',
  max_tokens: 4096,
  messages: [
    { role: 'user', content: 'What are the latest developments in artificial intelligence?' }
  ],
  tools: [{
    type: 'web_search_20250305',
    name: 'web_search',
    max_uses: 5,
  }],
});

const response = await stream.finalMessage();

for (const block of response.content) {
  if (block.type === 'text') {
    console.log(block.text);
  }
}

Response includes server_tool_use, web_search_tool_result, and text blocks with citations:

{
  "content": [
    {
      "type": "server_tool_use",
      "id": "srvtoolu_abc123",
      "name": "web_search",
      "input": { "query": "latest AI developments" }
    },
    {
      "type": "web_search_tool_result",
      "tool_use_id": "srvtoolu_abc123",
      "content": [{
        "type": "web_search_result",
        "url": "https://example.com/ai-news",
        "title": "AI News Today",
        "encrypted_content": "..."
      }]
    },
    {
      "type": "text",
      "text": "Recent AI developments include...",
      "citations": [{
        "type": "web_search_result_location",
        "url": "https://example.com/ai-news",
        "title": "AI News Today",
        "cited_text": "Recent breakthroughs in..."
      }]
    }
  ]
}

Web search requires models with tool use support. Check the Model Library to confirm web search support for specific models.