Catalog/Google/Ai mode
POST

Google Ai mode API

/v1/run/google.ai_mode

Ask Google AI Mode a prompt and receive the cited answer it generates. AI Mode composes the answer at search time, so repeat calls on one prompt can differ in wording and in which sources are cited.

Category SearchRequests / mo 6Routing 2 lanes · auto failover
Get ~100 free requests

Provider network

Providers ranked by traffic

click a provider for traffic and endpoints · routing stays automatic
Request
Gateway request
discovered operation
↓
Router
↓
↳ Calls hit the first lane first; on timeout or 5xx we retry down the ladder. Fallback order: Badger → Octopus

Try it

Make your first request

run it free, no key · same shape for every API
Open in
Get a free key
Sample response
Free runs return only the first 3 results. Fund a key to get the full response.
{
  "data": {
    "answer": "example",
    "answerMarkdown": "example",
    "citations": [
      {
        "title": "Example title",
        "url": "https://example.com/page"
      }
    ],
    "prompt": "example"
  },
  "found": true
}
Response interface
interface GoogleAiModeResponse {
  data: {
    answer: string;
    answerMarkdown: string;
    citations: {
      title: string;
      url: string;
    }[];
    prompt: string;
  } | null;
  found: boolean;
}

Full parameter and response reference - every field, type, and example for this endpoint.

Reference

Request, response, and price

Last verified 2026-08-23 · uptime and latency measured over 30d
POST /v1/run/google.ai_mode
curl -X POST https://api.getanyapi.com/v1/run/google.ai_mode \
  -H "Authorization: Bearer $ANYAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"What is AnyAPI at getanyapi.com, and what does it offer?"}'
FieldTypeExample value
Request body
promptstring"What is AnyAPI at getanyapi.com, and what does it offer?"The question or prompt to answer with Google AI Mode.
Response
dataobjectThe normalized answer, or null when no answer was found. Google composes the answer at search time rather than serving a stored one, so the same prompt can return different wording and a different set of citations on each call. Treat a response as one observation of the answer, not as a stable document.
data.answerstringThe answer as plain text, as Google generated it for this search. Length and coverage vary between searches on the same prompt. Populated whenever the provider has data for the entity.
data.answerMarkdownstringThe answer in Markdown when Google returns a Markdown rendering, otherwise the same text as answer. Populated whenever the provider has data for the entity.
data.citationsobject[]The sources Google cited for this search, in the order it returned them. Google recomputes the set per search, so counts and membership vary between calls on the same prompt.
data.citations[].titlestringThe cited source title.
data.citations[].urlstringThe cited source URL.
data.promptstringThe prompt answered by the upstream search experience. Populated whenever the provider has data for the entity.
foundbooleanWhether Google AI Mode returned an answer.
Price
Price per requestUSD$0.00126
Price /1k reqUSD$1.26

FAQ

About the Google Ai mode API

The AnyAPI Google Ai mode API returns Google ai mode data as normalized JSON from one POST call to /v1/run/google.ai_mode. Ask Google AI Mode a prompt and receive the cited answer it generates. AI Mode composes the answer at search time, so repeat calls on one prompt can differ in wording and in which sources are cited. AnyAPI routes each request across 2 sources and falls back automatically when one fails. It costs from $1.26 per 1,000 requests, in US dollars with no subscription and no monthly minimum. Over the last 30 days, 100.0% of Google ai mode calls through AnyAPI succeeded, with a median response time of 26.3 seconds across 6 measured calls.

It costs from $1.26 per 1,000 requests, in US dollars with no subscription and no monthly minimum. You fund one USD wallet, each call draws it down, and a failed request costs $0.

Ask Google AI Mode a prompt and receive the cited answer it generates. AI Mode composes the answer at search time, so repeat calls on one prompt can differ in wording and in which sources are cited. The response is normalized JSON with the same envelope every AnyAPI endpoint returns, so parsing a second endpoint is a change of URL and nothing else.

Over the last 30 days, 100.0% of Google ai mode calls through AnyAPI succeeded, with a median response time of 26.3 seconds across 6 measured calls. These are AnyAPI's own measurements of traffic through the gateway, recomputed continuously, not a published service-level target.

Get started

Two ways to start on AnyAPI

Humans fund a USD wallet and pay per request. Agents point a coding agent at one URL and onboard themselves.

Get ~100 free requests
Works with
Terminal agentsClaude CodeCursorCodexMCP clients