Web Search
Let supported models run web searches from /v1/responses or /v1/messages.
Web search is not a separate endpoint. You enable it by adding the hosted
search tool to a normal generation request. Use web_search with
POST /v1/responses, or Anthropic's web_search_20250305 tool with
POST /v1/messages.
Responses API
curl https://api.tryarcflow.com/v1/responses \
-H "Authorization: Bearer sk-..." \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5.5",
"input": "What is the latest Node.js LTS version?",
"tools": [{ "type": "web_search" }]
}'Messages API
curl https://api.tryarcflow.com/v1/messages \
-H "Authorization: Bearer sk-..." \
-H "anthropic-version: 2023-06-01" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-sonnet-4-6",
"max_tokens": 1024,
"messages": [{ "role": "user", "content": "What is the latest Node.js LTS version?" }],
"tools": [{ "type": "web_search_20250305", "name": "web_search", "max_uses": 5 }]
}'Notes
- Each search counts as server tool use and is metered.
- Claude Messages responses include
server_tool_usein theirusageblock, so you can see how many searches the model ran. - Use
max_usesto cap the number of searches per request.