Jiqizhixin APIjiqizhixin.com ↗
Access AI articles, full content, and open-source SOTA project data from Jiqizhixin via 6 endpoints. Browse, filter, search, and retrieve full article HTML and project details.
What is the Jiqizhixin API?
The Jiqizhixin API exposes 6 endpoints for retrieving AI research articles and open-source SOTA project data from 机器之心, one of China's leading AI media platforms. Use get_article_list to paginate the article library with titles, slugs, categories, tags, and content previews, or call get_article_detail with a slug to retrieve the full HTML body, author info, and publication timestamp. SOTA project browsing and keyword search are also covered.
curl -X GET 'https://api.parse.bot/scraper/c303912a-7465-4e9e-bd4c-64c646e0caea/get_article_list?per=5&page=1&sort=time' \ -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 jiqizhixin-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.
from parse_apis.jiqizhixin_机器之心_api import Jiqizhixin, Article, ArticleDetail, ProjectEntry, Project, SearchTerm
client = Jiqizhixin()
# Browse recent articles
for article in client.articles.list(sort="time", limit=5):
print(article.title, article.slug, article.published_at)
# Fetch full content of the first article
first_article = client.articles.get(slug="2026-06-10-13")
detail = first_article.details()
print(detail.title, detail.author.name, detail.published_at)
# Search SOTA projects and get details
for term in client.projectentries.search(query="language model"):
print(term.id, term.name)
# List SOTA project entries and drill into one
for entry in client.projectentries.list(limit=3):
print(entry.name, entry.slug, entry.total_stars)
project = entry.details()
print(project.name, project.desc, project.status)
Fetch a paginated list of articles from the article library, ordered by publication time. Each article includes title, slug, category, tags, author name, publication date, cover image URL, and a content preview. Paginate by incrementing `page`; total available count is returned for client-side page-count math.
| Param | Type | Description |
|---|---|---|
| per | integer | Results per page. |
| page | integer | Page number (1-based). |
| sort | string | Sort order. Accepted value: 'time'. |
{
"type": "object",
"fields": {
"success": "boolean indicating request success",
"articles": "array of article summary objects with id, title, slug, category, tagList, author, publishedAt, content preview, coverImageUrl",
"totalCount": "integer total number of articles available"
},
"sample": {
"data": {
"success": true,
"articles": [
{
"id": "d1ae21fc-5fcf-49db-8098-0ad1c7b99374",
"slug": "2026-06-10-13",
"title": "阿里搞了个免费报志愿Agent，40万AI考生提前把坑踩完了",
"author": "机器之心",
"source": "机器之心",
"content": "编辑｜杨文、泽南Agent 这个词...",
"tagList": [
"阿里巴巴",
"高考志愿填报 Agent",
"千问App"
],
"category": "industry",
"publishedAt": "2026/06/10 21:03",
"coverImageUrl": "https://image.jiqizhixin.com/uploads/article/cover_image/d1ae21fc-5fcf-49db-8098-0ad1c7b99374/0_-_2026-06-10T205715.399.jpg"
}
],
"totalCount": 29942
},
"status": "success"
}
}About the Jiqizhixin API
Article Endpoints
get_article_list returns a paginated array of article objects, each carrying id, title, slug, category, tagList, author, publishedAt, a content preview, and coverImageUrl. The per and page params control pagination, and passing sort=time orders results chronologically. The totalCount field tells you how many articles exist in the library. Once you have a slug, get_article_detail returns the complete article: title, an author object (with id, avatar_url, and name), the full content as an HTML string, and published_at.
SOTA Project Endpoints
get_sota_project_list pages through open-source AI projects. Each item in the data array includes a source object with name, slug, summary, category, techTags, and desc, alongside highlight and userFav fields. You can filter by category or sort by generationAt. get_sota_project_detail accepts a project slug and returns the full record: id, slug, name, summary, desc in Markdown, category, techTags, status, and teamInfo.
Search and Homepage Feed
search_sota_projects accepts a query string and returns a terms array of matching objects, each with id and name — useful for resolving project names before calling get_sota_project_detail. get_homepage_feed mirrors the article list with default parameters and requires no inputs, making it a quick way to pull the latest published articles without constructing pagination arguments.
The Jiqizhixin API is a managed, monitored endpoint for jiqizhixin.com — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when jiqizhixin.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 jiqizhixin.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 the latest AI research articles published on 机器之心 by polling
get_homepage_feedand detecting newpublishedAtvalues. - Build a Chinese-language AI newsletter by extracting full article HTML via
get_article_detailand reformatting for email delivery. - Index SOTA project metadata (name, summary, techTags, category) from
get_sota_project_listinto a searchable internal database. - Filter open-source AI projects by category using the
categoryparam inget_sota_project_listto surface domain-specific tools. - Resolve project slugs before detailed lookups by running keyword queries through
search_sota_projectsand matching returnedidandnamefields. - Track article coverage by topic by aggregating
tagListandcategoryfields across paginated results fromget_article_list. - Compare project descriptions and team metadata across multiple SOTA entries using
desc,status, andteamInfofromget_sota_project_detail.
| 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 Jiqizhixin offer an official public developer API?+
What does `get_article_detail` return beyond the article text?+
get_article_detail returns the full article body as an HTML string in the content field, plus the title, a published_at timestamp, and an author object containing id, name, and avatar_url. It does not return comment counts or engagement metrics.Can I filter `get_article_list` by tag or category?+
get_article_list accepts per, page, and sort parameters. Filtering by tag or category is not currently supported at the endpoint level — you would need to filter on tagList or category fields in the returned objects client-side. You can fork the API on Parse and revise it to add a category or tag filter parameter.Does the SOTA search endpoint return full project details?+
search_sota_projects returns only id and name per matching term — it is designed for term resolution, not full record retrieval. To get the full project record including desc, techTags, status, and teamInfo, pass the resolved slug to get_sota_project_detail.Are author profiles or journalist pages available as a separate endpoint?+
id, avatar_url, name) inside article responses. Standalone author profile pages with article history or bio content are not covered. You can fork the API on Parse and revise it to add a dedicated author endpoint.