surfaces: ["google_ai_mode"]AI Mode is Google’s full conversational answer experience, a step past AI Overviews, with its own retrieval, links and presentation, and no official API. We render it in a browser and return the answer with its sources and observed sub-queries inline as the same canonical Envelope every other surface uses.
curl -sS -X POST "https://api.aisearchapi.dev/v1/search" \
-H "Authorization: Bearer $AISEARCH_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "compare electric suv range 2026",
"surfaces": ["google_ai_mode"],
"regions": [{ "country": "US" }]
}'
# → 202 { "jobId": "…", "children": ["….google_ai_mode.…"] }
# 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 Google AI Mode actually populates. Field names below are the contract, not a summary.
answer.text · answer.markdown · answer.blocksThe full AI Mode answer as rendered, typically longer and more structured than an Overview, normalized into typed blocks.
answer.markdown (inline links + sub-queries)The links AI Mode surfaces, and the sub-questions it prints, come through inline in the answer markdown, ready for your own extraction.
provenancerequested-vs-effective region, surfacePresent, triggerState, the capture self-describes.
provenance.regionRequested-vs-effective country per capture, so cross-market AI Mode comparisons are trustworthy.
html (opt-in proof-of-page)Set include.html:true and the Envelope carries a top-level html URL — a proof-of-page snapshot of the rendered AI Mode experience, fetchable at GET /v1/artifacts/{key}. Off by default.
{
"job": {
"id": "job_e19b3fa2.google_ai_mode.US",
"surface": "google_ai_mode",
"status": "completed",
"warnings": []
},
"provenance": {
"surfacePresent": true,
"region": { "requested": "US", "effective": "US" }
},
"answer": {
"text": "Range leaders in 2026: Lucid Gravity, then…",
"markdown": "Range leaders in 2026: **Lucid Gravity** [lucidmotors.com], then…\n\nSearches run:\n- 2026 electric SUV range\n- fastest-charging electric SUVs",
"blocks": [ { "type": "paragraph", "text": "…" } ]
}
}Google’s AI Mode captured live from the real experience.
Phase-2 surfaces are roadmap, not product. Requesting one returns an honest 422 today. The full picture is on the coverage page.
An AI Overview is a block on the classic results page; AI Mode is the full conversational search experience with its own deeper retrieval and presentation. They cite differently and trigger differently, which is why they are separate surfaces here, google_ai_mode and google_ai_overview, each with its own Envelope per capture.
Browser render of the real AI Mode experience (there is no official API for it).
AI Mode decomposes your query into multiple sub-searches before composing its answer, and it often prints those sub-queries right in the response. When it does, they come through in answer.markdown, the closest thing that exists to seeing the retrieval behind Google’s answer, and the input GEO teams use to target the queries that actually get searched.
Four credits per successful capture, everything included, charged only on success. 500 free credits to start.
Yes, one request with multiple regions fans out into one child Envelope per country (any ISO-3166 country, up to 10 per request), each with requested-vs-effective geo recorded.
500 free credits, charged only on success, and the same Envelope for every other surface when you add them.