For AI
View as MarkdownOpen in ChatGPTOpen in Claude

WeChat Search suggestions API

Get the suggestions WeChat Search lists in its search box for a keyword, in the order it lists them, about 10 at a time. The words and their places only, with no index. About 9 items a call, 20 at most; $0.1 per call. Errors and timeouts are not charged; an empty result is charged $0.1.

GEThttps://api.dataxapi.com/v1/wechat/keywords/related
Also known aswechat search suggestionswechat autocomplete keywordsweixin search suggestwechat related searchesIn Chinese: 微信搜一搜推荐词 API
Price$0.1/ call · Errors and timeouts are not charged
Returnsup to 20 a pageeverything in one answer, no paging
When an upstream failsRetried for youon the same route, or a backup route; never charged
StatusLive statusChecked daily with real calls · 13 days on record

Try it

Change a value and the request on the right follows.
Run · $0.1

Sign in to run it; it runs on your own balance. New accounts can try this endpoint free, up to 1 calls.

The first 4 rows of a response recorded 2026-10-29 09:50 UTC for 露营地小程序.
FieldValue
keyword露营地小程序
related_to露营
relationsuggestion
rank1
curl -G "https://api.dataxapi.com/v1/wechat/keywords/related" \
  --data-urlencode "keyword=咖啡" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"
{
  "code": "ok",
  "request_id": "b959d32d-16f5-4907-a8fe-3d74bb6c0b6c",
  "data": {
    "items": [
      {
        "keyword": "露营地小程序",
        "related_to": "露营",
        "relation": "suggestion",
        "rank": 1
      },
      // … 8 more
    ]
  },
  "page": {
    "next_cursor": null,
    "cursor_expires_at": null,
    "has_more": false,
    "returned": 9
  },
  "warnings": [],
  "meta": {
    "capability": "wechat.keywords.related",
    "result_status": "complete",
    "fetched_at": "2026-10-29T09:50:02.000Z",
    "cached": false,
    "replayed": false,
    "unavailable": {
      "relevance": "platform",
      "search_index": "platform",
      "composite_index": "platform"
    },
    "billing": {
      "amount": "0.1",
      "currency": "USD",
      "balance_after": "9.9"
    }
  }
}

From a response recorded 2026-10-29 09:50 UTC. Names, text and IDs are examples, and so are the links: none is the recorded one (the page shows no one's personal data); the figures are as recorded. Long lists are cut. The request ID, cursor and balance are made up.

Size as sent: 1.3 KB in the standard view (1.3 KB compact, 1.3 KB full).

{
  "code": "ok",
  "request_id": "63423bfc-2b8d-49b4-89a4-05265dcb346f",
  "data": { "items": [] },
  "page": {
    "next_cursor": null,
    "cursor_expires_at": null,
    "has_more": false,
    "returned": 0
  },
  "warnings": [],
  "meta": {
    "capability": "wechat.keywords.related",
    "result_status": "empty",
    "fetched_at": "2026-10-29T09:50:02.000Z",
    "cached": false,
    "replayed": false,
    "unavailable": {
      "relevance": "platform",
      "search_index": "platform",
      "composite_index": "platform"
    },
    "billing": {
      "amount": "0.1",
      "currency": "USD",
      "balance_after": "9.9"
    }
  }
}

From a recording of 2026-10-29 09:50 UTC, edited by hand to show this case. The request ID and balance are made up.

Size as sent: 483 B in the standard view (483 B compact, 483 B full).

This example as a JSON file

curl -G "https://api.dataxapi.com/v1/wechat/keywords/related" \
  --data-urlencode "keyword=咖啡" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"
# pip install dataxapi
from dataxapi import DataXAPI

dx = DataXAPI()  # reads DATAXAPI_API_KEY
result = dx.wechat.keywords.related(keyword="咖啡")
print(result["data"]["items"])
// npm i @dataxapi/sdk
import { DataXAPI } from "@dataxapi/sdk";

const dx = new DataXAPI(); // reads DATAXAPI_API_KEY
const result = await dx.wechat.keywords.related({ keyword: "咖啡" });
console.log(result.data.items);
dataxapi call wechat.keywords.related 'keyword=咖啡'
{
  "mcpServers": {
    "dataxapi": {
      "type": "http",
      "url": "https://api.dataxapi.com/mcp",
      "headers": {
        "Authorization": "Bearer ${DATAXAPI_API_KEY}"
      }
    }
  }
}

Add this to your MCP client, then ask your agent to call wechat.keywords.related.

Parameters

keywordtextrequired

One keyword. Example: 咖啡.

viewtext

How much of each item to return. All three cost the same. Values: compact, standard (default), full.

fieldslist of text

Return only these fields. Each by its path, such as author.name.

Known limits

Returned fields

data.items is a list of related keyword objects. Preview: the structure may change, announced beforehand.

keywordtextcompact

The related keyword

related_totextcompact

The keyword it is related to: the one asked about

relationtextcompact

How it is related: query (searched together with the keyword asked about), posts (appears together with it in content), prior (searched before it), after (searched after it), suggestion (what the platform suggests as the keyword is typed into its search box)querypostsprioraftersuggestion

rankintegercompact

Position by relevance among the keywords of the same relation, from 1

On this platform: Place among the suggestions the search box lists, from 1, the keyword asked about itself not counted

relevancenumbercompactThe platform has none

How closely it is related to the keyword asked about, 0 to 1

search_indexintegercompactThe platform has none

Search index of the related keyword: the platform's index, not a count of searches; null where the platform gives no figure for the word

Show all 10 fields →
composite_indexintegercompactThe platform has none

Composite index of the related keyword: the platform's index of how much attention content about it drew, not a count

approximatelist of objectcompact

Which numbers of this item are approximate or lower bounds; absent when all are exact

approximate[].fieldtextcompact

Path of the field, such as metrics.views

approximate[].kindtextcompact

Approximate, or a lower boundapproximatelower_bound

Typical size of one item: compact 90 B, standard 90 B, full 90 B (measured on the response recorded 2026-10-29 09:50 UTC).

What this endpoint cannot give

relevanceThe platform has none
search_indexThe platform has none
composite_indexThe platform has none

When you are charged

A result with data$0.1, once per call
An empty result$0.1
Invalid parameters, a failure of ours or of the data source, a timeoutnot charged
CaseCharged
The most one call can cost$0.1 (send X-Max-Price to refuse anything above your own limit)

Prices as read 2026-10-30 14:10 UTC, under price book 6, in effect since 2026-10-29 13:23 UTC; the Playground reads the price in force before a run.

If the object does not exist

A keyword WeChat Search has no suggestions for returns an empty result, never a not-found error.

Errors

What this endpoint can answer with; codes all endpoints share are on the full list.

HTTPCodeMeaningCharged
400invalid_paramsA parameter is invalidRetry: After a fixNo
402insufficient_balanceThe balance is too lowRetry: After a fixNo
502upstream_failedThe data source failedRetry: YesNo
504timeoutThe data did not arrive in time; retry with the same idempotency keyRetry: YesNo

All error codes →

Questions

How much does the WeChat Search suggestions API cost?

$0.1 per call. The most one call can cost is $0.1.

When am I not charged?

Errors and timeouts are not charged; an empty result is charged $0.1.

How many items does one call return, and how do I get the next page?

About 9 items a page, 20 at most. The page size is the platform's; limit is not accepted. Everything comes in one page; no cursor is issued.

What happens if the object does not exist?

A keyword WeChat Search has no suggestions for returns an empty result, never a not-found error.

30-day availability

13 days are on record. The share is written here once 14 days are.

It is not a success rate: how single calls went is not in it, and a failed call is not charged either way.

Every endpoint's state now, and each incident with whether anyone was charged: the status page →

All 5 WeChat Search endpoints

WeChat Search endpoints
WeChat Search articles and videos$0.0200WeChat Search articles and videos (backup)$0.1WeChat Index$0.1WeChat Search suggestions$0.1WeChat mini program search$0.1

Use it in your AI

Copy this prompt

Your API key is built in, so there is nothing to configure.

Read https://dataxapi.com/agents.md and set up DataXAPI in this agent. My API key is dx_…; use it for every DataXAPI call.
Sign in to copy it with your key

No account yet? Sign-up takes an email and no card, and a failed call is never charged.

then paste

Paste it into your agent

It reads the page the prompt points to and connects itself.

Your agent
Read https://dataxapi.com/agents.md and set up DataXAPI in this agent. My API key is dx_••••; use it for every DataXAPI call.
DataXAPI connected · 5 tools ready
now try it

Now ask something

Use one of these, or your own words.

Read https://dataxapi.com/apis/wechat/keywords/related.md and help me use the DataXAPI endpoint wechat.keywords.related (WeChat Search suggestions).
Prefer to set it up by hand?
dataxapi setupgives the agents on your machine (Claude Code, Codex, Cursor) the DataXAPI MCP server and the base skill. The key is read from DATAXAPI_API_KEY; none is written into a file.MCP server: https://api.dataxapi.com/mcp. The entry for your client is under MCP in the request examples of this page; then ask your agent to call wechat.keywords.related.Other clients →
Ask with this pageSends the Markdown version
Open in ChatGPTOpen in ClaudeOther clients →
Brief for an AIEverything needed to call it, as text
Show the text
Use the DataXAPI endpoint wechat.keywords.related (WeChat Search suggestions). Get the suggestions WeChat Search lists in its search box for a keyword, in the order it lists them, about 10 at a time. The words and their places only, with no index.
Call GET https://api.dataxapi.com/v1/wechat/keywords/related with the header "Authorization: Bearer $DATAXAPI_API_KEY". Read the key from the environment variable DATAXAPI_API_KEY; never write it into code.
Parameters:
- keyword (required): One keyword. Example: 咖啡.
- view: How much of each item to return. All three cost the same. Values: compact, standard (default), full.
- fields: Return only these fields. Each by its path, such as author.name.
Price: $0.1 per call. Errors and timeouts are not charged; an empty result is charged $0.1.
The answer is JSON: data.items holds related keyword; meta.billing.amount is what this call was charged.
Example:
curl -G "https://api.dataxapi.com/v1/wechat/keywords/related" \
  --data-urlencode "keyword=咖啡" \
  -H "Authorization: Bearer $DATAXAPI_API_KEY"
Full reference in Markdown: https://dataxapi.com/apis/wechat/keywords/related.md

Names and identifiers

In Chinese
微信搜一搜推荐词 API
Endpoint ID
wechat.keywords.related
Endpoint
GET /v1/wechat/keywords/related
Last checked 2026-10-30 14:10 UTC.View the Markdown versionopenapi.jsonllms.txt

Start with one key.

224 endpoints on 21 platforms, from $0.0003 a call. Errors and timeouts are not charged.

Start free