Gemini API

Gemini Search API

Ask Gemini a web-grounded question and receive an answer with source citations.

POST/v1/run/gemini.search
Uptime
73.42%
30d · 79 calls
Requests
79
30d · weekly, last 12 wks
Response
22.3s
median · 30d

Pricing

One price, in dollars

Providers
Owl51 served78.46% uptime18853ms p50$4.80/1k reqflatBadgerNot serving7 served22.58% uptime35503ms p50$2.00/1k reqflat

A provider marked Not serving stopped answering reliably and was taken out of the rotation, so your calls go to the others. It is put back on its own once it answers reliably again.

Try it

Make your first request

Loading...

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

Reference

Request, response, and price

Last verified 2026-09-29 · uptime and latency measured over 30d
FieldTypeExample value
Price
Price per requestUSD$0.0048
Price /1k reqUSD$4.80

FAQ

About the Gemini Search API

The AnyAPI Gemini Search API returns Gemini search data as normalized JSON from one POST call to /v1/run/gemini.search. Ask Gemini a web-grounded question and receive an answer with source citations. AnyAPI returns one normalized schema whichever source serves it. It costs from $4.80 per 1,000 requests, in US dollars with no subscription and no monthly minimum. Over the last 30 days, 73.4% of Gemini search calls through AnyAPI succeeded, with a median response time of 22.3 seconds across 79 measured calls.

It costs from $4.80 per 1,000 requests, in US dollars with no subscription and no monthly minimum. You fund one USD wallet and each call draws it down. Some failed wallet-funded requests incur processing charges that we pass through at cost, with no markup; the error response shows the amount charged.

Ask Gemini a web-grounded question and receive an answer with source citations. 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, 73.4% of Gemini search calls through AnyAPI succeeded, with a median response time of 22.3 seconds across 79 measured calls. These are AnyAPI's own measurements of traffic through the gateway, recomputed continuously, not a published service-level target.