TrendForce APIinsights.trendforce.com ↗
Retrieve TrendForce Insights articles and post listings via API. Access full article text sections, figures, tags, authors, and metadata for AI chip and semiconductor analysis.
What is the TrendForce API?
The TrendForce Insights API exposes 2 endpoints for accessing semiconductor and AI industry analysis from insights.trendforce.com. The list_posts endpoint returns paginated post summaries with keyword search and sort controls, while get_post delivers full article content broken into text_sections and figures — including alt text, captions, tags, authors, subtitle, wordcount, and publication date — structured for direct LLM ingestion.
curl -X GET 'https://api.parse.bot/scraper/fbe93ce5-a6bd-4c39-8e93-3a714d6de4c4/list_posts?sort=new&limit=5&offset=0' \ -H 'X-API-Key: $PARSE_API_KEY'
Typed, relational, agent-ready
A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.
- Fully typed · autocompletes
- Objects link to objects
- Typed errors & pagination
Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:
uv add parse-sdk uv run parse init uv run parse add --marketplace insights-trendforce-com-api
uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.
"""TrendForce Insights: browse semiconductor/AI articles and read full content."""
from parse_apis.trendforce_insights_api import TrendForce, Sort, PostNotFound
client = TrendForce()
# List the latest posts sorted by popularity, capped to 5 items.
for summary in client.postsummaries.list(sort=Sort.TOP, limit=5):
print(summary.title, summary.reaction_count, summary.wordcount)
# Search for a specific topic and drill into the first result's full article.
result = client.postsummaries.list(search="AI chip", sort=Sort.NEW, limit=1).first()
if result:
post = result.details()
print(post.title, post.post_date)
for section in post.text_sections[:3]:
print(section.tag, section.content[:100])
for fig in post.figures[:2]:
print(fig.alt, fig.caption)
# Fetch a post directly by slug via the posts collection.
try:
direct = client.posts.get(slug="ai-inference-chip-architecture")
print(direct.title, direct.wordcount, direct.authors)
except PostNotFound as exc:
print(f"Post not found: {exc.slug}")
print("exercised: postsummaries.list / PostSummary.details / posts.get / PostNotFound")
List and search posts from TrendForce Insights. Supports sorting by newest or most popular, keyword search, and pagination via offset/limit. Returns post summaries including engagement metrics (reactions, comments) and metadata. Each post summary carries a slug usable with get_post to retrieve full article content.
| Param | Type | Description |
|---|---|---|
| sort | string | Sort order for posts. |
| limit | integer | Maximum number of posts to return per request. |
| offset | integer | Pagination offset (number of posts to skip). |
| search | string | Search query to filter posts by keyword. Empty string returns all posts. |
{
"type": "object",
"fields": {
"count": "integer total number of posts returned in this response",
"posts": "array of post summary objects with id, slug, title, subtitle, description, post_date, canonical_url, cover_image, wordcount, reaction_count, comment_count, tags, and authors",
"offset": "integer current pagination offset"
},
"sample": {
"data": {
"count": 1,
"posts": [
{
"id": 201420960,
"slug": "computex-2026-cpo-in-focus",
"tags": [
"Co-Packaged Optics (CPO)",
"COMPUTEX",
"Silicon Photonics (SiPh)"
],
"title": "COMPUTEX 2026: CPO in Focus",
"authors": [
"TrendForce"
],
"subtitle": "",
"post_date": "2026-06-11T04:01:30.348Z",
"wordcount": 778,
"cover_image": "https://substack-post-media.s3.amazonaws.com/public/images/76d874a2-35be-4b84-b14b-5c3f2e376290_1202x631.jpeg",
"description": "Following our previous COMPUTEX 2026 report on memory, this piece turns to another standout theme of the event: Co-Packaged Optics (CPO) technology.",
"canonical_url": "https://insights.trendforce.com/p/computex-2026-cpo-in-focus",
"comment_count": 0,
"reaction_count": 5
}
],
"offset": 0
},
"status": "success"
}
}About the TrendForce API
Post Listings
The list_posts endpoint returns a count, a posts array of summary objects, and the current offset. You can sort results by new (most recent) or top (most popular), paginate using limit and offset, and filter by keyword with the search parameter — for example, passing 'NVIDIA' or 'HBM' scopes results to matching articles. Leaving search as an empty string returns all posts.
Full Article Content
The get_post endpoint takes a slug — either copied from a URL path like ai-inference-chip-architecture or pulled from a list_posts result — and returns the complete article. The response includes title, subtitle, authors, post_date, wordcount, tags, and cover_image as metadata fields. Article body content is split into text_sections (paragraphs, headings, list items, and blockquotes) and figures (each with src, alt, and caption). This split makes it straightforward to feed article text and image descriptions into downstream language model pipelines without additional parsing.
Coverage and Scope
TrendForce Insights focuses on semiconductors, memory, display panels, AI chips, and related supply chain topics. Articles are authored by TrendForce analysts and cover market share estimates, technology roadmaps, and supply/demand forecasts. The tags field on each post signals the topic cluster, and authors identifies the analyst responsible — useful for filtering by subject-matter specialization.
The TrendForce API is a managed, monitored endpoint for insights.trendforce.com — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when insights.trendforce.com changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.
This isn't an official insights.trendforce.com API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.
Will this API break when the source site changes?+
Is this an official API from the source site?+
Can I fix or extend this API myself if I need a new endpoint or field?+
What happens if I call an endpoint that has an issue?+
- Monitor new TrendForce analyst reports on AI inference chips by polling
list_postswithsort=newand a relevantsearchkeyword - Build a semiconductor news digest by fetching
text_sectionsfromget_postand summarizing with an LLM - Index TrendForce articles by
tagsto track coverage of specific topics like HBM, TSMC, or edge AI over time - Extract
figureswith captions from chip architecture articles to populate a visual reference database - Aggregate
authorsandpost_datefields to analyze publishing cadence and analyst focus areas - Feed
wordcountandsubtitlefields into a content scoring pipeline to prioritize long-form research for deeper analysis - Search for competitor mentions across articles using the
searchparameter inlist_poststo track how frequently specific companies appear
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 100 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 100 req/min |
One credit = one API call regardless of which marketplace API you call. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does TrendForce offer an official developer API for insights.trendforce.com?+
What does `get_post` return beyond the article text?+
id, slug, title, subtitle, authors (array), tags (array), post_date, wordcount, and cover_image as metadata. The body is divided into text_sections — covering paragraphs, headings, list items, and blockquotes — and figures, each containing src, alt, and caption. Premium or paywalled content that requires a TrendForce subscription is not exposed by the endpoint.Can I filter `list_posts` results by tag, author, or date range?+
search parameter and sorting by new or top. Filtering by specific tag, author, or date range is not available. You can fork this API on Parse and revise it to add those filter parameters.Is there a way to get comment counts, view counts, or social engagement metrics for each post?+
list_posts response returns post summaries and the get_post response covers article content and metadata; neither exposes engagement metrics such as comment counts or view counts. You can fork this API on Parse and revise it to add an engagement data endpoint if that surface is accessible.How does pagination work in `list_posts`?+
limit to set the number of posts per request and offset to skip a number of posts from the beginning of the result set. The response always includes count (total matching posts) so you can calculate how many pages remain. There is no cursor-based pagination — only numeric offset.