Search API for AI applications.
Search the web, news or images and get structured results as JSON or Markdown. Scrape the top results or get a grounded answer in the same call.
- 500 free credits every month
- No card to start
- Failed requests cost nothing
Try it on your own search






Search results your AI can use.
Most search APIs stop at titles, links and snippets. Geekflare can also fetch the pages behind the results or write a grounded answer, all in the same request.
Search and scrape in one call
Turn on scrape and get the top results with their page content ready for LLMs. No second round of requests to fetch every link.
scrape: trueGrounded answers
Get an AI answer based on live search results. Good for answer engines, research tools, and chat assistants.
groundedAnswer: trueWeb, news and images
Use the same endpoint to search the web, news, or images depending on what your application needs.
source: web | news | imagesCountry and time filters
Search from a specific country and limit results by time from the last hour to the last year, or a custom window such as the past seven days.
location: inDomain and category filters
Keep results to the sources you trust, exclude sites you don't want, or narrow the search to code or research.
category: code | researchLLM-ready output
Ads and noise are stripped before results reach you. Take them as JSON or Markdown for a model's context.
format: json | markdownWhat customers say.
“Its been couple of years we are using Geekflare API, we like its stable production ready performance and cost-effectiveness of accessing multiple APIs through a single plan.”
Jitendra RauloDirector, Aarav Infotech“I've been using Geekflare for both their API tools and their multi-AI chat platform. The URL-to-Markdown API has been a game changer for my content pipeline.”
“Found Geekflare API to get markdown from URL for my AI agents. It is fast and cheaper and works on almost every website.”
Ram DasiArchitect, PA ConsultingSearch from where your users are.
The same query returns different results in different countries. Set a location and you get the results people there see, for local SEO, market research and regional news.
locationtakes an ISO country code such as"de"or"in"- Pair it with
source: "news"andtimefor regional news - Included in every search at no extra cost
- 195
- Countries
- City
- Narrowest targeting available
The parameters you'll use most.
What each one does and what it costs.
- querystring—
What to search for. Up to 2,048 characters.
- limitnumberIncluded
Number of results, from 1 to 100. Defaults to 10.
- sourcestringIncluded
web, news or images. Defaults to web.
- locationstringIncluded
Country to search from, as an ISO code such as "us" or "de".
- citystringIncluded
City to search from, from the list of supported cities, such as "London,England,United Kingdom". Takes priority over location.
- timestringIncluded
h, d, w, m or y, or a custom window such as d7 for the last seven days.
- categorystringIncluded
general, code, pdf, research, linkedin or wiki.
- includeDomainsstring[]Included
Only return results from these domains. excludeDomains does the opposite.
- formatstringIncluded
json or markdown. Defaults to json.
- scrapeboolean+0.25–1 per page
Also fetch the content of the top results. Set how many with scrapeLimit, from 1 to 10.
- serpbooleanIncluded
Return Google's first results page as structured JSON: ranked organic results, AI Overview, People Also Ask and related searches. See the SERP API.
- groundedAnswerboolean+3
Synthesize an AI answer from the search results.
| Parameter | Type | What it does | Credits |
|---|---|---|---|
| query | string | What to search for. Up to 2,048 characters. | — |
| limit | number | Number of results, from 1 to 100. Defaults to 10. | Included |
| source | string | web, news or images. Defaults to web. | Included |
| location | string | Country to search from, as an ISO code such as "us" or "de". | Included |
| city | string | City to search from, from the list of supported cities, such as "London,England,United Kingdom". Takes priority over location. | Included |
| time | string | h, d, w, m or y, or a custom window such as d7 for the last seven days. | Included |
| category | string | general, code, pdf, research, linkedin or wiki. | Included |
| includeDomains | string[] | Only return results from these domains. excludeDomains does the opposite. | Included |
| format | string | json or markdown. Defaults to json. | Included |
| scrape | boolean | Also fetch the content of the top results. Set how many with scrapeLimit, from 1 to 10. | +0.25–1 per page |
| serp | boolean | Return Google's first results page as structured JSON: ranked organic results, AI Overview, People Also Ask and related searches. See the SERP API. | Included |
| groundedAnswer | boolean | Synthesize an AI answer from the search results. | +3 |
What people do with the Search API.
An answer, not a page of links
Search the live web and get a grounded answer synthesized from the results in a single request. Give answer engines and support assistants current information without building the search-to-answer pipeline yourself.
- One call instead of search, fetch and summarize
- Grounded in current web results, not model knowledge alone
- Results in seconds
POST /search
{
"query": "latest openai model",
"groundedAnswer": true
}Your first search, in a few lines.
# pip install geekflare-api
from geekflare_api.client import GeekflareClient
from geekflare_api.models import SearchRequestDto
with GeekflareClient(api_key="<api-key>") as client:
result = client.search(
SearchRequestDto(
query="best running shoes"
)
)
print(result)One API. Every stack.
One account works from an agent, a workflow builder, an SDK or your own service.
MCP server
Sign in once and Claude, ChatGPT, Cursor or Codex can use Geekflare's tools directly, with no glue code to write.
LLM & agent pipelines
LLM-ready Markdown straight into a retrieval pipeline, with the boilerplate stripped so you spend context on content, not navigation.
Workflow builders
Run any endpoint as a step in a visual scenario. Useful when the person who needs the data does not write code.
SDKs & REST
First-party typed SDKs for Python and Node. Everything else talks plain REST, from any language.
How many searches each plan covers.
What a search costs depends on what you ask it to return. Failed requests cost nothing.
| Covered per month | Free $0/mo No card | Starter $19/mo | Most popular Growth $69/mo | Business 500K $299/mo | Business 1M $499/mo |
|---|---|---|---|---|---|
Credits a month | 500 | 20,000 | 100,000 | 500,000 | 1,000,000 |
SearchesWeb, news and images, or Google's results page with serp.2 credits | 250 | 10,000 | 50,000 | 250,000 | 500,000 |
Searches with 3 full pagesThe results plus each page at its Web Scraping cost, counted here at 1 credit a page.5 credits | 100 | 4,000 | 20,000 | 100,000 | 200,000 |
Searches with an AI answerA grounded answer written from the results.5 credits | 100 | 4,000 | 20,000 | 100,000 | 200,000 |
| Requests per second | 1 | 5 | 10 | 25 | 25 |
- Free$0/moNo card
- Credits a month
- 500
- Searches2 credits
- 250
- Searches with 3 full pages5 credits
- 100
- Searches with an AI answer5 credits
- 100
- Requests per second
- 1
- Starter$19/mo
- Credits a month
- 20,000
- Searches2 credits
- 10,000
- Searches with 3 full pages5 credits
- 4,000
- Searches with an AI answer5 credits
- 4,000
- Requests per second
- 5
- GrowthMost popular$69/mo
- Credits a month
- 100,000
- Searches2 credits
- 50,000
- Searches with 3 full pages5 credits
- 20,000
- Searches with an AI answer5 credits
- 20,000
- Requests per second
- 10
- Business 500K$299/mo
- Credits a month
- 500,000
- Searches2 credits
- 250,000
- Searches with 3 full pages5 credits
- 100,000
- Searches with an AI answer5 credits
- 100,000
- Requests per second
- 25
- Business 1M$499/mo
- Credits a month
- 1,000,000
- Searches2 credits
- 500,000
- Searches with 3 full pages5 credits
- 200,000
- Searches with an AI answer5 credits
- 200,000
- Requests per second
- 25
Before you integrate search.
Everything else is in the endpoint docs, and our support team replies to every email.
Open the endpoint docsscrape it costs 2 credits plus each page's Web Scraping cost: 0.25 credits for a page that loads without a browser and 1 for one that needs JavaScript, so 10 pages cost 4.5 to 12 credits. A grounded answer costs 5 credits per request. Failed requests cost nothing.scrape and we also visit the top results and return their full page content in the same response, so your AI gets the actual context, not just a list of links.groundedAnswer: true and we use AI to synthesize an answer from the live search results, so you get a direct answer in one request instead of searching, fetching and summarizing yourself.source. Filter by country with location, by recency with time, by type with category (code, pdf, research, linkedin, wiki), and by site with includeDomains and excludeDomains.limit (10 by default). With scrape on, scrapeLimit sets how many of them are fetched in full, from 1 to 10.serp: true to get Google's first results page as structured JSON, with ranked organic results, People Also Ask and related searches, at the same price as a search. When Google shows an AI Overview for the query, you get its text and sources too. The SERP API page has the details.format: "markdown" the HTML, navigation and ads are gone, which cuts token usage and helps the model focus on the content.scrape on, response time also depends on how fast the result pages load.Ask AI about Geekflare
Open the question in the assistant you already use.
250 searches a month, free.
No card needed, and it renews every month. Try it on a question your users would ask.