/v1/call/douyin.brand_historyDouyin trend-index brand trends API
Only on Douyin.
Get a brand's day-by-day search, content and spread indexes on Douyin over a date range, from the platform's own index tool. An index is the platform's score, not a count; days are calendar days in China time (UTC+8). A call to the Douyin trend-index brand trends API costs 2 credits ($0.004 to $0.0067 depending on the pack); failed calls are free. Call it over HTTP or from your AI client over MCP.
Last updated:
What you get from the Douyin trend-index brand trends API.
From a recorded answer.
A recorded call returned the object below, field by field. Names and text are removed from the sample; the numbers are as recorded.
Lighter for your AI: the same recorded data (1 item) is about 7,477 tokens as the platform's raw JSON and about 1,292 as this interface returns it, 82% fewer (measured 2026-11-06). How it was measured
| Field | In the recorded answer |
|---|---|
| title | 泡泡玛特 |
| url | null |
| rank | null |
| heat | null |
| fields.category | 母婴 |
| fields.points | 7 entries |
2 credits a call (≈ $0.004–$0.0067): about 1,500 calls for $10.
Douyin trend-index brand trends API: request and response
curl https://socialtoai.app/v1/call/douyin.brand_history \ -H "Authorization: Bearer $SOCIALTOAI_API_KEY" \ -H "Idempotency-Key: $(uuidgen)" \ -H "Content-Type: application/json" \ -d '{ "brand": "泡泡玛特", "since": "2026-09-01T00:00:00Z", "until": "2026-09-30T00:00:00Z" }'import osimport uuidimport requestsresponse = requests.post( "https://socialtoai.app/v1/call/douyin.brand_history", headers={ "Authorization": f"Bearer {os.environ['SOCIALTOAI_API_KEY']}", # A new key for each request; the same one again retries it without paying twice. "Idempotency-Key": str(uuid.uuid4()), }, json={ "brand": "泡泡玛特", "since": "2026-09-01T00:00:00Z", "until": "2026-09-30T00:00:00Z", },)print(response.json())# Connected over MCP? Ask in plain words.Use the Douyin trend-index brand trends interface (douyin.brand_history) with brand: 泡泡玛特, since: 2026-09-01T00:00:00Z, until: 2026-09-30T00:00:00Z.# Your AI calls the call tool with:{ "brand": "泡泡玛特", "since": "2026-09-01T00:00:00Z", "until": "2026-09-30T00:00:00Z"}{ "op": "douyin.brand_history", "platform": "douyin", "status": "ok", "items": [ { "platform": "douyin", "id": "泡泡玛特", "ref": "泡泡玛特", "approx": [], "extra": {}, "type": "entry", "entry_type": "brand_history", "title": "泡泡玛特", "url": null, "rank": null, "heat": null, "fields": { "category": "母婴", "points": [ { "date": "2026-09-01T00:00:00Z", "search_index": 121864, "content_index": 41224, "spread_index": 75601 }, { "date": "2026-09-02T00:00:00Z", "search_index": 122413, "content_index": 46057, "spread_index": 77637 }, { "date": "2026-09-03T00:00:00Z", "search_index": 122213, "content_index": 45504, "spread_index": 77642 }, { "date": "2026-09-04T00:00:00Z", "search_index": 122205, "content_index": 54042, "spread_index": 78337 }, { "date": "2026-09-05T00:00:00Z", "search_index": 124682, "content_index": 42229, "spread_index": 77377 }, { "date": "2026-09-06T00:00:00Z", "search_index": 124155, "content_index": 42738, "spread_index": 76569 }, { "date": "2026-09-07T00:00:00Z", "search_index": 121751, "content_index": 41525, "spread_index": 76108 } ] } } ], "unavailable": [], "cost_credits": 2}- entry_type
- brand_history
- category
- 母婴
Names and text were removed from the sample; the numbers are as recorded.
Douyin trend-index brand trends API parameters.
3 parameters, all required.
Send them as a JSON body with POST. Your key goes in the Authorization header, never in the URL.
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| brand | string | Required | — | The brand's name, spelled as the index lists it |
| since | datetime | Required | — | The first day wanted: the China-time (UTC+8) calendar day this moment falls on |
| until | datetime | Required | — | The last day wanted, read the same way. The platform publishes a day or two late: a day it has no figure for yet has a null index |
Douyin trend-index brand trends API response fields.
What Douyin cannot give is marked.
| Field | Type | Meaning |
|---|---|---|
| items[].extra | object | What the platform gives of this item beyond the fields below, under the platform's own names (an IP location, a uid, a showcase flag); the interface's extra_fields says what each is. Empty when there is nothing more. Of a comment or a review, never who wrote it. |
| items[].title | string | The entry's title or name. |
| items[].url | string | A link that opens it; null where the platform's list has none. |
| items[].rank | integer | Position on a board, from 1. |
| items[].heat | integer | The platform's heat score. |
| items[].fields.category | string | The industry the platform puts the brand in, in the platform's words. |
| items[].fields.points | array | One entry per day, oldest first: date, search_index, content_index, spread_index. |
nullFields Douyin cannot giveDouyin gives every field of this call. Where one item lacks a value, that field is null.
Every item also has platform, id, ref, approx and type; the response around the items is the same on every call. Response format
Douyin trend-index brand trends API: paging and billing.
5 calls per second per key, 20 after a purchase; going over is not charged. Rate limits
A failed call costs 0 credits and is never retried on its own. Error codes
Interface last tested: 2026-10-17. Each call reads from the platform, and fetched_at in the answer is when it was read. The same request sent again with the same key within 5 minutes is a replay (replayed: true): 0 credits, and the answer as first read.
Once connected over MCP, these questions use the Douyin trend-index brand trends API.
Get a brand's day-by-day search, content and spread indexes on Douyin over a date range, from the platform's own index tool (brand: 泡泡玛特, since: 2026-09-01T00:00:00Z, until: 2026-09-30T00:00:00Z).
2 creditscall {"op":"douyin.brand_history","brand":"泡泡玛特","since":"2026-09-01T00:00:00Z","until":"2026-09-30T00:00:00Z"}
Give this to your AI.
Copy it into Claude or ChatGPT.
How to connectUse the SocialToAI MCP server (https://socialtoai.app/mcp) for this: Get a brand's day-by-day search, content and spread indexes on Douyin over a date range, from the platform's own index tool (brand: 泡泡玛特, since: 2026-09-01T00:00:00Z, until: 2026-09-30T00:00:00Z).Call the call tool with {"op":"douyin.brand_history","brand":"泡泡玛特","since":"2026-09-01T00:00:00Z","until":"2026-09-30T00:00:00Z"}. Needed: brand, since, until.For several, call it once for each: 2 credits each.Before you start, work out how many credits it will take in all and ask me; call it only after I agree.What usually comes next, with the ref or username it returns: call douyin.keyword_history (Trend-index keyword trends).If SocialToAI is not connected yet, tell me how to connect it; never ask me to paste a key into the chat.Answer with a link to every item you used, and tell me how many credits it cost.Paste it into a chat once SocialToAI is connected over MCP. There is no key in it: Claude and ChatGPT sign in, other clients send a key in a header.
Read next.
What its own API allows, who can use it and what it costs, with sources.
Keywords, brands, creators and topics: all 10 on one page.
connect Claude to the comments under Douyin videos
connect Claude Code and Cursor to Xiaohongshu and Douyin with no QR code or cookie, and what a self-run server costs you
monitor Xiaohongshu, Douyin and Weibo from outside China with AI, in English, with original links
the website or the interfaces: which suits what, and a real request
Let your AI read Douyin.