serp is a Google search results service for application development and information retrieval, not a conversational generative model. It accepts keywords or query statements and returns program-friendly JSON, covering web, image, news, video, place, and map searches. Combined with controls for region, language, time range, and pagination, it is suitable for building research discovery, keyword monitoring, and AI assistant retrieval workflows.
Submit requests to the public API at api.acedata.cloud using the documented parameters, then use the results in your application.
Input parameters and result formats vary by service. Use the public API for this model and follow its guide for generation, task retrieval and editing operations.
Clarify capacity, input/output, and invocation methods before selecting a solution.
The above are the invocation specifications for the serp search endpoint, not the context or output capacity of a generative model; the actual number of results and additional information vary by query.
Learn what serp can bring to your work.
A single entry point lets you switch between web pages, images, news, videos, places, and maps, without sending every task to standard web search. Use search to look up company information, news to find coverage, and places to discover local businesses, making your input goal better match the result category.
Search results are returned as JSON, making it easy to extract titles, links, snippets, and ranking positions, then continue with deduplication, display, or storage. Standard search may also return related questions, related searches, and a knowledge graph, helping applications expand query directions instead of receiving only a block of text that is difficult to split.
With country, language, and range, you can organize searches around target markets and time windows. For example, set the country and language separately for the same brand, then query information from the past day or week. page and number control pagination and the number of requests, making it easier to collect results according to task scale.
Start with specific tasks to find where the model can be effective.
Enter brand terms, product terms, or industry keywords, and save the titles, links, and positions from web results to create search records for comparison. When querying regularly, keep regional, language, and pagination conditions consistent to help monitor competitor pages and keyword performance; recording and comparison logic is organized by the application itself.
Use a company name or event topic as the query, select news, and set a time range to organize returned titles, snippets, links, and available dates into a list of coverage leads. Suitable for editorial planning and brand information monitoring; you should still open the original text to verify details rather than treating short snippets as complete reports.
Have the assistant first turn user questions into queries, then pass search results to a language model for summarization and citation organization. Clients that support MCP can also use categorized search tools through SerpMCP. serp is responsible for discovering information and returning links, while final answers, web reading, and multi-step execution are handled by the assistant workflow.
Choose based on task complexity, input materials, and expected results.
If the task requires internet links, search snippets, result positions, or related queries, serp is a better fit than asking a generative model to answer solely from its existing knowledge. If the deliverable is a long-form article, explanation, or comprehensive analysis, you can first use serp to obtain materials and then pass them to a language model for processing; it does not generate articles itself, nor does it automatically read all matched webpages.
The key to choosing serp is the search mode, not version upgrades of generative models. For general information discovery, use search; for recent reporting, use news; for image and video discovery, use images and videos respectively; for local businesses, use places or maps. The direct API is suitable for embedding in programs, while MCP is suitable for invocation by compatible clients; neither represents a different model generation.
First prepare the inputs, then connect them to the appropriate application workflow.
Prepare clear query terms, choose a web or news type, and set the language, region, and required time range.
Choose types such as search, news, or images based on the needed results, save search criteria and pagination first, then add result titles, links, and snippets to the materials list. Before consolidating conclusions, return to key sources to verify the full text.
Design tasks directly from the following inputs and acceptance priorities.
Use /serp/google to search for official product information, retaining the title, link, snippet, and search criteria for each result; record page numbers when paginating.
Open key sources one by one and check whether the publication date and full text support the conclusions; search snippets are for discovering materials and cannot replace full-text verification.
Before formal use, understand output quality and capability scope.
Answers to common questions when using serp.
No. serp is a Google search results service that returns structured search data after receiving a query, rather than generating conversations. It is suitable for finding webpages, news, or other resources; when explanations, writing, and integrated judgment are needed, search results can be passed to a language model for further processing.
Send a POST request to /serp/google, use a Bearer Token, and provide query in the JSON request body; no model is needed. The default type is search, the page number is 1, and the requested number is 10; the query cannot contain only whitespace characters, and do not add undefined parameters.
Set type to news, fill query with event or brand keywords, and use d or qdr:d for range. When targeting a specific market, country and language can also be set. Returned content is for discovering recent coverage; specific publication times and event details should still be confirmed against the original text.
No, serp searches existing images and does not generate new images. When type is images, image_size can be used to set large, medium, icon, or supported mp filter tiers; other search types cannot carry this field. Image links in the results also do not mean that permission for use has been obtained.
A single search request will not automatically complete webpage reading or multi-step research. serp returns links, summaries, and available additional information, which applications can use to choose what to read next. When used through MCP, search is only one tool available to the assistant; the complete task is still organized and executed by the client.
Choose a development approach or application suited to this model and follow its setup guide.
↗↗
↗
↗
↗