Douyin and Xiaohongshu search box suggestions (autocomplete) by API, in bulk (2026)
Douyin's is douyin.keywords.related and Xiaohongshu's xiaohongshu.keywords.related: send 1 keyword and get the about 10 suggestions that platform's search box lists for it, with their places, at $0.0200 a call each; WeChat Search's is wechat.keywords.related. The free trial covers up to 333 calls; a failed call is not charged.
All three answer in one shape: 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 with no suggestions returns an empty result.
Platform
Endpoint
Price
Douyin
douyin.keywords.related
$0.0200
Xiaohongshu
xiaohongshu.keywords.related
$0.0200
WeChat Search
wechat.keywords.related
$0.1
How do suggestions differ from related keywords?
Suggestions are what the platform completes as people type, which tells what they search. The related keywords of the platforms' tools are another thing: 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. Both serve finding topics: widen the words with suggestions, then weigh them by index.
How do I get them in bulk?
In an AI: “Get the Douyin and Xiaohongshu search box suggestions of these 30 words and make one table: platform, word, suggestion, place.” It calls once a word a platform. A script is the same loop.
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.
Why DataXAPI
Steady: endpoints were available 99.9% of the last 30 days, on a public status page you can check.
Fast: a paid call took 2.5 seconds at the median over the last 7 days (counted 2026-11-06).
Fewer tokens: across 226 endpoints, one recorded real response each, the platform's own JSON comes to 9.2M tokens and what an AI reads through DataXAPI's MCP server to 452k, 95% fewer; the JSON of a direct API call is 90% 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.