Hugging Face Papers API
Keyword search across papers, or the newest papers, with abstracts, upvotes and AI summaries.
GET /v1/hugging-face/papers1 credit Failed requests are free
About this endpoint
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.
Hugging Face Papers API 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.
Other Hugging Face endpoints
- Search modelsGET /v1/hugging-face/models
- Get modelGET /v1/hugging-face/models/{owner}/{name}
- Search datasetsGET /v1/hugging-face/datasets
- Get datasetGET /v1/hugging-face/datasets/{owner}/{name}
- Search SpacesGET /v1/hugging-face/spaces
- Get SpaceGET /v1/hugging-face/spaces/{owner}/{name}
- READMEGET /v1/hugging-face/repos/{repoType}/{owner}/{name}/readme
- FilesGET /v1/hugging-face/repos/{repoType}/{owner}/{name}/files