/v1/call/xiaohongshu.search_suggestionsXiaohongshu (RedNote) search suggestions API
Only on Xiaohongshu.
Get the suggestions Xiaohongshu's search box lists as a keyword is typed into it (autocomplete), in the order it lists them, about 10 at a time. The words and their places only, with no index. A call to the Xiaohongshu (RedNote) search suggestions API costs 12 credits ($0.024 to $0.04 depending on the pack); failed calls are free. Call it over HTTP or from your AI client over MCP.
Last updated:
Daily watch: tell your AI “watch this daily” and this call runs by itself every day, sending only what is new: at most 372 credits a month, about $1.24. How to set it up
What you get from the Xiaohongshu (RedNote) search suggestions API.
From a recorded answer.
A recorded call returned 10 items; here is the first, field by field. Names and text are removed from the sample; the numbers are as recorded.
| Field | In the recorded answer |
|---|---|
| title | 露营必备清单 |
| url | null |
| rank | 1 |
| heat | null |
| fields.related_to | 露营 |
| fields.relation | suggestion |
| fields.relevance | null: Xiaohongshu cannot give it |
| fields.search_index | null: Xiaohongshu cannot give it |
| fields.composite_index | null: Xiaohongshu cannot give it |
12 credits a call (≈ $0.024–$0.04): about 250 calls for $10.
Xiaohongshu (RedNote) search suggestions API: request and response
curl https://socialtoai.app/v1/call/xiaohongshu.search_suggestions \ -H "Authorization: Bearer $SOCIALTOAI_API_KEY" \ -H "Idempotency-Key: $(uuidgen)" \ -H "Content-Type: application/json" \ -d '{ "keyword": "露营" }'import osimport uuidimport requestsresponse = requests.post( "https://socialtoai.app/v1/call/xiaohongshu.search_suggestions", 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={ "keyword": "露营", },)print(response.json())# Connected over MCP? Ask in plain words.Use the Xiaohongshu search suggestions interface (xiaohongshu.search_suggestions) with keyword: 露营.# Your AI calls the call tool with:{ "keyword": "露营"}{ "op": "xiaohongshu.search_suggestions", "platform": "xiaohongshu", "status": "ok", "items": [ { "platform": "xiaohongshu", "id": "露营必备清单", "ref": "露营必备清单", "approx": [], "extra": {}, "type": "entry", "entry_type": "keyword_related", "title": "露营必备清单", "url": null, "rank": 1, "heat": null, "fields": { "related_to": "露营", "relation": "suggestion", "relevance": null, "search_index": null, "composite_index": null } } ], "unavailable": ["fields.relevance", "fields.search_index", "fields.composite_index"], "page": { "has_more": false }, "cost_credits": 12}- entry_type
- keyword_related
- related_to
- 露营
- relation
- suggestion
- relevance
null- search_index
null- composite_index
null
Names and text were removed from the sample; the numbers are as recorded.
Xiaohongshu (RedNote) search suggestions API parameters.
1 parameter, 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 |
|---|---|---|---|---|
| keyword | string | Required | — | One keyword |
Xiaohongshu (RedNote) search suggestions API response fields.
What Xiaohongshu 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.related_to | string | The keyword you asked about. |
| items[].fields.relation | string | How it is related: query (searched together with your keyword), posts (appears with it in content), prior (searched before it), after (searched after it), suggestion (offered as your keyword is typed into the search box). |
| items[].fields.relevance | numberalways null | How closely it is related to your keyword, from 0 to 1. |
| items[].fields.search_index | integeralways null | The related keyword's search index: the platform's own index, not a count of searches. null where the platform gives no figure for the word. |
| items[].fields.composite_index | integeralways null | The related keyword's composite index: the platform's own index of how much attention content about it drew, not a count. |
nullFields Xiaohongshu cannot giveRead null as “Xiaohongshu did not give this”, not as zero. These are always null on this call:
fields.relevanceHow closely it is related to your keyword, from 0 to 1.fields.search_indexThe related keyword's search index: the platform's own index, not a count of searches. null where the platform gives no figure for the word.fields.composite_indexThe related keyword's composite index: the platform's own index of how much attention content about it drew, not a count.
Every item also has platform, id, ref, approx and type; the response around the items is the same on every call. Response format
Xiaohongshu (RedNote) search suggestions 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: 2026-11-20. 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 Xiaohongshu (RedNote) search suggestions API.
Get the suggestions Xiaohongshu's search box lists as a keyword is typed into it (autocomplete), in the order it lists them, about 10 at a time: 露营.
12 creditscall {"op":"xiaohongshu.search_suggestions","keyword":"露营"}
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 the suggestions Xiaohongshu's search box lists as a keyword is typed into it (autocomplete), in the order it lists them, about 10 at a time: 露营.Call the call tool with {"op":"xiaohongshu.search_suggestions","keyword":"露营"}. Needed: keyword.It gives its first page only, up to 20 items, with no next page; each call costs 12 credits.Before you start, work out how many credits it will take in all and ask me; call it only after I agree.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.
The interface of the same name on other platforms.
All platforms and prices/v1/call/xiaohongshu.search_suggestions{ "keyword": "露营" }12 creditsper callRead next.
What its own API allows, who can use it and what it costs, with sources.
connect ChatGPT to Xiaohongshu notes and comments
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
Let your AI read Xiaohongshu.