> **For coding agents and LLMs:** This is one Social Fetch marketing page (markdown export). For API orientation start with [`/llms.txt`](https://www.socialfetch.dev/llms.txt); for auth and crawl rules use [`/agents.txt`](https://www.socialfetch.dev/agents.txt); for every operation use [`/llms-endpoints.txt`](https://www.socialfetch.dev/llms-endpoints.txt).

## This page

- **On-site (HTML):** <https://www.socialfetch.dev/platforms/hugging-face/papers>
- **Markdown (.mdx) URL:** <https://www.socialfetch.dev/platforms/hugging-face/papers.mdx>

---

# Hugging Face Papers API

Keyword search across papers, or the newest papers, with abstracts, upvotes and AI summaries.

`GET /v1/hugging-face/papers` returns a page of `papers` and a `page` block. Without `query` it lists the newest papers and pages with `page.nextCursor`. With `query` it searches titles, abstracts and metadata; a search returns one page of up to 120 papers and sets `page.hasMore` to false.

Each paper has `id`, `title`, `url`, `summary`, `publishedAt`, `upvotes`, `numComments`, `thumbnailUrl`, `githubRepo`, `githubStars`, `organization`, `submittedBy`, `submittedOnDailyAt`, `aiSummary` and `aiKeywords`. `limit` accepts up to 100.

## Request

- **Endpoint:** `GET /v1/hugging-face/papers`
- **Credits:** 1 credit
Failed requests are free
- **Input:** by keyword
- **Full reference:** [docs](https://www.socialfetch.dev/docs/api/v1/hugging-face/papers/get)
- **Platform page:** [/platforms/hugging-face](https://www.socialfetch.dev/platforms/hugging-face)

## FAQ

### Why can I not page past the first search result?

A keyword search returns up to 120 papers in one page and has no continuation. Only the newest-papers list pages with page.nextCursor.

### What is in summary?

The paper's abstract. aiSummary is a shorter summary the platform generated, and aiKeywords lists the generated keywords.

### Can I get the full text here?

No. Use GET /v1/hugging-face/papers/{arxivId}/content for the markdown text.

### How much does a paper page cost?

Pricing is documented on the operation in the API registry (shown on this page). Confirm on every response with meta.creditsCharged: that field is the billing source of truth. Each paginated page is a separate billed request.