Weibo & Xiaohongshu Data APIs Now on SandBase

TL;DR — 100 new social media data operations: 64 for Weibo (hot search, public timelines, app-level user data — all at $0.001/call) and 36 for Xiaohongshu (blogger analytics via PGY, note details, product recommendations — $0.001-$0.02/call). Both platforms use the same /v1/run contract as every other SandBase capability.

Two platforms, two fundamentally different data profiles. Weibo is China’s real-time public square — breaking news, trending opinions, brand crises surface here first. Xiaohongshu is China’s consumption decision engine — product reviews, lifestyle content, and KOL recommendations drive purchase behavior.

An agent that monitors both captures the full spectrum: what people are talking about (Weibo) and what they are buying (Xiaohongshu).

Weibo: 64 operations, 3 channels

Channel	Operations	What it covers	Price
`weibo/web-v2/*`	23	Hot search, topic trends, public posts, user timelines	$0.001
`weibo/app/*`	17	App-level user data, relationship graphs, post details	$0.001
`weibo/web/*`	10	Legacy web endpoints, profile data, comment threads	$0.001

Every single Weibo operation costs $0.001. No tiers, no surprises.

What Weibo data enables for agents

Real-time trend detection: weibo/web-v2/hot-search returns the current hot search list with topic heat scores. An agent polling every 15 minutes catches brand mentions, industry trends, or crisis signals within one cycle.

Sentiment sampling: Combine hot search detection with weibo/web-v2/topic-posts to pull top posts for a flagged topic. Feed into an LLM for sentiment classification.

Competitive positioning: Track how competitors are discussed on Weibo. weibo/app/user-timeline gives you a competitor’s official Weibo post history; weibo/web-v2/post-comments gives you public reactions.

Example: brand crisis detection workflow

import requests
from openai import OpenAI

SANDBASE_API_KEY = "sk-..."
HEADERS = {
    "Authorization": f"Bearer {SANDBASE_API_KEY}",
    "Content-Type": "application/json",
}

# OpenAI client for LLM calls only
client = OpenAI(base_url="https://api.sandbase.ai/v1", api_key=SANDBASE_API_KEY)

# Step 1: Check hot search for brand mentions (direct HTTP)
hot_search = requests.post(
    "https://api.sandbase.ai/v1/run",
    headers=HEADERS,
    json={"model": "weibo/web-v2/hot-search"},
).json()

# Step 2: For each relevant topic, pull posts (direct HTTP)
topic_posts = requests.post(
    "https://api.sandbase.ai/v1/run",
    headers=HEADERS,
    json={"model": "weibo/web-v2/topic-posts", "topic_id": "flagged_topic_id", "count": 20},
).json()

# Step 3: LLM sentiment analysis (OpenAI SDK — correct for LLMs)
analysis = client.chat.completions.create(
    model="anthropic/claude-sonnet-4",
    messages=[{
        "role": "user",
        "content": f"Analyze sentiment of these Weibo posts about our brand:\n{topic_posts}"
    }]
)

Cost per cycle: 1 hot search + 3 topic fetches + 1 LLM call = ~$0.015/cycle. Running every 15 minutes: $1.44/day.

Xiaohongshu: 36 operations, 3 channels

Channel	Operations	What it covers	Price
`xiaohongshu/app-v2/*`	20	Note details, user profiles, search, product recommendations, faved notes	$0.001-$0.01
`xiaohongshu/pgy/*`	10	PGY (蒲公英) influencer platform: blogger lists, detail, fans history, campaign data	$0.02
`xiaohongshu/web-v3/*`	6	Homepage feed, hot lists, trending content	$0.001-$0.01

Xiaohongshu pricing has two tiers: basic content data at $0.001-$0.01, and PGY (蒲公英, Xiaohongshu’s official influencer marketplace) data at $0.02.

What Xiaohongshu data enables for agents

KOL screening: xiaohongshu/pgy/blogger-list returns influencers filtered by category, follower range, engagement metrics. xiaohongshu/pgy/blogger-detail gives deep analytics per creator. An agent can screen 200 KOLs for $4.

Content trend analysis: xiaohongshu/web-v3/hot-list shows what’s trending on Xiaohongshu right now. Combine with xiaohongshu/app-v2/search-images to find visual content patterns in your product category.

Product intelligence: xiaohongshu/app-v2/product-recommendations reveals what products are being recommended alongside yours. xiaohongshu/app-v2/user-faved-notes shows what content is being saved (high-intent signal).

Example: KOL evaluation per candidate

# Get blogger overview with engagement metrics
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "xiaohongshu/pgy/blogger-detail", "blogger_id": "5f3a..."}'

# Get their fans growth trend
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "xiaohongshu/pgy/blogger-fans-history", "blogger_id": "5f3a..."}'

Cost per KOL evaluation: 2 PGY calls × $0.02 + 2 content calls × $0.001 = $0.042/KOL. Screen 100 candidates: $4.20.

Cross-platform scenarios

Scenario: product launch monitoring

A consumer brand launches a new product. The agent monitors both platforms in parallel:

Platform	What to monitor	Endpoints	Cost/day
Weibo	Brand mentions in hot search, post sentiment	hot-search + topic-posts	$0.10
Xiaohongshu	Product-related notes, competitor recommendations	search + product-recommendations	$0.05
Total			$0.15/day = $4.50/month

Scenario: influencer campaign performance

After a KOL campaign launch, track real-time performance:

Metric	Weibo endpoint	Xiaohongshu endpoint
Post engagement	`weibo/web-v2/post-comments`	`xiaohongshu/app-v2/note-detail`
Audience reaction	`weibo/app/post-reposts`	`xiaohongshu/app-v2/note-comments`
Creator growth	`weibo/app/user-profile`	`xiaohongshu/pgy/blogger-fans-history`

What SandBase adds

Both platforms share the same runtime benefits as every other capability in the SandBase ecosystem:

One contract: Weibo GET queries and Xiaohongshu POST bodies both normalize to {"model": "...", ...params} through /v1/run
Cross-platform composition: A single workflow can call Weibo hot search → Xiaohongshu product search → LLM analysis without switching APIs or auth methods
Cost tracking: See exactly how much each platform costs per agent session in your traces
Skill reuse: Package “daily brand health check across Weibo + XHS” as one invocable skill

Limitations

Weibo: All 64 operations are read-only. No posting, no direct messaging. Weibo’s official API with OAuth is needed for write operations.
Xiaohongshu: 36 operations cover analytics and content discovery, not account management. PGY data ($0.02/call) reflects Xiaohongshu’s own influencer platform pricing.
Both: Public data access through third-party infrastructure, not official platform authorization. Data freshness varies: hot search is near-real-time, historical analytics may lag.

FAQ

How does Weibo data pricing compare to Douyin?

Identical. All 64 Weibo operations cost $0.001/call — the same as 79% of Douyin operations. Weibo has no premium tier because its endpoints are simpler (mostly public timeline and search data vs Douyin’s creator analytics).

What can I learn from Xiaohongshu PGY data?

PGY (蒲公英) is Xiaohongshu’s official influencer marketplace. PGY data includes: blogger engagement scores, follower demographics, content category classification, campaign history, and fans growth curves. It’s the same data brands see when evaluating KOLs on Xiaohongshu’s own platform.

Can I track a specific Xiaohongshu note’s performance over time?

Yes. Call xiaohongshu/app-v2/note-detail periodically to track likes, comments, saves, and shares. At $0.001/call, tracking 50 notes daily costs $0.05/day.

Is there overlap between Weibo and Douyin coverage?

Minimal. They serve different platforms with different user behaviors. Weibo is text + opinion-first (trending topics, comments, reposts). Douyin is video-first (creators, engagement metrics, commerce). Most monitoring agents use both.

For the complete picture of social media data options, see our social media data API guide. For Douyin-specific coverage, see 310 Douyin APIs on SandBase.