Skip to content
Docs

Advanced Features

Give Claude access to the web, bound how long a provider may take, and cache prompt prefixes between calls. For controlling how much Claude thinks before answering, see Extended thinking.

Web search

Use the built-in web search tool to give the model access to current information from the web.

Example request
web-search.sh
curl -X POST "https://ai-gateway.vercel.sh/v1/messages" \
  -H "Authorization: Bearer $AI_GATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-5",
    "max_tokens": 2048,
    "tools": [
      {
        "type": "web_search_20250305",
        "name": "web_search"
      }
    ],
    "messages": [
      {
        "role": "user",
        "content": "What are the latest developments in quantum computing?"
      }
    ]
  }'
web-search.ts
import Anthropic from '@anthropic-ai/sdk';
 
const apiKey = process.env.AI_GATEWAY_API_KEY || process.env.VERCEL_OIDC_TOKEN;
 
const anthropic = new Anthropic({
  apiKey,
  baseURL: 'https://ai-gateway.vercel.sh',
});
 
const message = await anthropic.messages.create({
  model: 'anthropic/claude-opus-5',
  max_tokens: 2048,
  tools: [
    {
      type: 'web_search_20250305',
      name: 'web_search',
    },
  ],
  messages: [
    {
      role: 'user',
      content: 'What are the latest developments in quantum computing?',
    },
  ],
});
 
for (const block of message.content) {
  if (block.type === 'text') {
    console.log(block.text);
  } else if (block.type === 'web_search_tool_result') {
    console.log('Search results received');
  }
}
web-search.py
import os
import anthropic
 
api_key = os.getenv('AI_GATEWAY_API_KEY') or os.getenv('VERCEL_OIDC_TOKEN')
 
client = anthropic.Anthropic(
    api_key=api_key,
    base_url='https://ai-gateway.vercel.sh'
)
 
message = client.messages.create(
    model='anthropic/claude-opus-5',
    max_tokens=2048,
    tools=[
        {
            'type': 'web_search_20250305',
            'name': 'web_search',
        }
    ],
    messages=[
        {
            'role': 'user',
            'content': 'What are the latest developments in quantum computing?'
        }
    ],
)
 
for block in message.content:
    if block.type == 'text':
        print(block.text)
    elif block.type == 'web_search_tool_result':
        print('Search results received')

Provider timeouts

You can set per-provider timeouts for BYOK credentials to trigger fast failover when a provider is slow to respond. Pass providerTimeouts in providerOptions.gateway:

"providerOptions": {
  "gateway": {
    "providerTimeouts": {
      "byok": { "anthropic": 3000, "bedrock": 5000 }
    }
  }
}

For full details, limits, and response metadata, see Provider Timeouts.

Automatic caching

Use caching: 'auto' in providerOptions.gateway to let AI Gateway automatically add cache_control breakpoints for Anthropic models. This removes the need to manually mark cacheable content.

For full details, supported providers, and examples, see Automatic Caching.

Last updated July 28, 2026
Previous
Images
Next
OpenResponses API

Was this helpful?

supported.