WeChat Search autocomplete suggestions API: getting them in bulk (2026)
Use wechat.keywords.related: send 1 keyword and get the about 10 suggestions WeChat Search lists in its box, with their places, at $0.1 a call. In bulk, call it once a word, from an AI or a loop in a script. DataXAPI reads WeChat Search with 6 endpoints, from $0.0200 a call; a failed call is not charged, and the free trial covers up to 333 calls.
One suggestion an item: keyword is the suggestion, related_to the word you asked about, rank its place in the box (from 1, the word asked about not counted). Words and places only, with no index; a word WeChat Search suggests nothing for returns an empty result.
How do I get them in bulk?
In an AI: “Get the WeChat Search suggestions for these 50 words and make one table: word, suggestion, place.” It calls once a word. A script is the same loop, one call a word.
To see which word is hotter, wechat.index.keywords.history gives its WeChat Index for the last 30 days; for the articles under it, wechat.posts.search.
To connect: paste this to your AI assistant: “Read https://dataxapi.com/agents.md and set up DataXAPI here. My API key is dx_…; use it for every DataXAPI call.” A client that takes a remote MCP server can be given https://api.dataxapi.com/mcp with the header Authorization: Bearer <key> instead.
And Douyin's and Xiaohongshu's suggestions?
They are there too, in the same shape: Douyin's search box suggestions are douyin.keywords.related and Xiaohongshu's xiaohongshu.keywords.related, at $0.0200 a call each. The related words of the platforms' tools are two more: douyin.index.keywords.related is Ocean Engine's related words, with relevance and index; xiaohongshu.pgy.keywords.related is the words PGY users search before and after a word, with a search index and note counts.
Why DataXAPI
Steady: endpoints were available 97.3% of the last 30 days, on a public status page you can check.
Fast: a paid call took 2.6 seconds at the median over the last 7 days (counted 2026-11-06).
Fewer tokens: across 6 endpoints on WeChat Search, one recorded real response each, the platform's own JSON comes to 67k tokens and what an AI reads through DataXAPI's MCP server to 13k, 81% fewer; the JSON of a direct API call is 71% fewer too (counted 2026-11-06). Every platform answers in one shape: the author in author, counts in metrics, the next page in page.next_cursor, so another platform needs no new parser.
See before you pay: every endpoint's page shows a recorded real response, field by field.
Spending you control: a failed call is not charged; each key can have a limit, X-Max-Price caps one call, and the same Idempotency-Key within 24 hours is never charged twice.
Ready for AI: a remote MCP server listed in the official MCP registry as com.dataxapi/mcp, usable from Claude, Cursor and ChatGPT.
Free trial of up to 333 calls, no card.
Endpoints
Each with its price; every page has the parameters, the fields and a recorded response.