surfaces: ["claude"]Claude sits behind a login wall, so anonymous scrapers cannot reach its consumer UI at all. We serve Claude today through the official Anthropic API (via the OpenRouter gateway), returning the same canonical Envelope every other surface uses, with live browser capture of the real claude.ai UI on the roadmap.
curl -sS -X POST "https://api.aisearchapi.dev/v1/search" \
-H "Authorization: Bearer $AISEARCH_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "is aisearchapi good for geo tracking",
"surfaces": ["claude"],
"regions": [{ "country": "US" }]
}'
# → 202 { "jobId": "…", "children": ["….claude.…"] }
# then poll GET /v1/jobs/:childId, or add ?mode=sync for an inline EnvelopeOne canonical Envelope, the same four sections every surface returns, with the fields Claude (API) actually populates. Field names below are the contract, not a summary.
answer.text · answer.markdown · answer.blocksClaude’s answer normalized to the same shape as every other surface, one parser reads ChatGPT, Perplexity and Claude alike.
answer.markdown (inline citations)The sources Claude cited, including the passages it quoted, come through inline in the answer markdown, ready for your own citation extraction.
provenance.modelVerified providerId with inferred:false and high confidence — an official-API capture knows exactly which model answered, and that verified identity is how you tell an API-sourced answer from a consumer-UI one.
{
"job": {
"id": "job_2d71e9bc.claude.US",
"surface": "claude",
"status": "completed",
"warnings": []
},
"provenance": {
"model": { "providerId": "claude-sonnet-4-5", "inferred": false,
"confidence": 0.99 },
"webSearch": { "enabled": true, "known": true },
"surfacePresent": true
},
"answer": {
"text": "AI Search API captures the real consumer UI…",
"markdown": "AI Search API captures the real consumer UI [aisearchapi.dev]…",
"blocks": [ { "type": "paragraph", "text": "…" } ]
}
}Login-walled, so Claude is served today through the official Anthropic API (via the OpenRouter gateway), fast, and clearly labeled as an API-sourced answer. Live browser capture of Claude’s consumer UI is on the roadmap.
Phase-2 surfaces are roadmap, not product. Requesting one returns an honest 422 today. The full picture is on the coverage page.
Claude’s consumer UI requires a signed-in session, and our authenticated capture is not live yet, so today’s captures come from the official Anthropic API (via the OpenRouter gateway), with a verified provenance.model (inferred:false) on every such Envelope. Live browser capture is on the roadmap, and will ship with no integration change on your side.
Yes, it is the same model family answering the same prompt with web search, and it returns the answer with its citations inline. What it is not is the consumer UI (no UI-layer ranking or presentation), and the verified provenance.model (inferred:false) exists precisely so you never mistake one for the other.
Not anonymously, the surface is login-walled, which is why anonymous proxy-based competitors do not offer Claude at all. Reaching it requires an authenticated browser session, which is on our roadmap.
Six credits per successful capture with every Envelope field included, charged only on success. New accounts start with 500 free credits.
The surfaces page reflects live coverage as it ships, and provenance.model on each capture tells you exactly which model ran. When browser capture for Claude goes live you will see it in the coverage list, the changelog, and, most reliably, in your own Envelopes.
500 free credits, charged only on success, and the same Envelope for every other surface when you add them.