I don't write code: how do I get my AI to fetch Official Account, Xiaohongshu and Douyin data? (2026)
It depends on 1 thing: whether your AI can add a tool. If it can (Claude Code, Cursor, Codex and the like), paste one sentence and it connects itself. If it only chats, have it write a short script you run. A call starts at $0.0020, and a failed call is not charged. DataXAPI reads WeChat Official Accounts with 8 endpoints, from $0.0200 a call; a failed call is not charged, and the free trial covers up to 333 calls.
Sign up, copy your key, and paste this: “Read https://dataxapi.com/agents.md and set up DataXAPI in this agent. My API key is dx_…; use it for every DataXAPI call.” Replace dx_… with your own key.
If your AI only chats
It cannot call the data itself, but it can write the script. Paste this, with no key in it: “I want to use DataXAPI to export ____ into a table. Its instructions are at https://dataxapi.com/agents.md. You cannot call it directly, so write a short Python script for my computer. Read the key from the environment variable DATAXAPI_API_KEY, save the result as CSV, and tell me how to run it and the most it can cost.”
Do not paste your key into a chat. The script reads it from your computer.
Things to ask for
Adding “tell me how many calls and what it costs before you start” keeps the spending in your hands.
What you want
Say this
Each call
An account's past articles
“Export the title, link and date of this Official Account's latest 100 articles into a table: ____”
$0.0200
What competitors posted
“List what these 5 Official Accounts published this week, with reads: ____”
$0.0200
What users complain about
“Read the comments on these Xiaohongshu notes and sort the complaints by how often they come up: ____”
$0.0200
Whether a word is rising
“Show how this word's Douyin index moved over the last 30 days: ____”
$0.0060
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 3.5 seconds at the median over the last 7 days (counted 2026-11-06).
Fewer tokens: across 8 endpoints on WeChat Official Accounts, one recorded real response each, the platform's own JSON comes to 21k tokens and what an AI reads through DataXAPI's MCP server to 4,494, 79% fewer; the JSON of a direct API call is 70% 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.