Hugging Face paper search API

Use the Hugging Face paper search API to retrieve paper titles, authors, abstracts and publication references. Enter paper-search words and a result limit to retrieve matching Hub paper entries, including authors, abstracts, community signals and source links without running a model. Find publications relevant to a research question, verify bibliographic details, or collect source links for a literature review. Abstracts, bibliographic identifiers and access links follow the indexed source record and do not guarantee access to restricted full text. The detail page provides request and response examples, supported parameters, and usage pricing.

Selected price
$0.002 / billing creditPublished pricing
Sellers / implementations
1 / 1
Requests · 30d
—Loading...
Success rate · 30d
—Loading...

Run sends a real API request. Charges follow the published API contract.

Request parameters
Search words.
Optional parameters (6)
Results per page (default 20, max 120).
0 leaves out the bulky `raw` source blocks (often 10-30x smaller).
Comma-separated fields to return, e.g. `posts.id,posts.title`. Call metadata is always included.
1 skips the 24-hour cache and fetches live.
JSON only for this OpenAny product. Omit output or use json; CSV and NDJSON exports are not exposed.
Native CSV/NDJSON record selector; it has no effect on this JSON-only product.

Sample response

{
  "cached": false,
  "count": 20,
  "credits_used": 1,
  "items": [
    {
      "ai_keywords": [
        "diffusion probabilistic models",
        "latent variable models",
        "… 9 more"
      ],
      "ai_summary": "Diffusion probabilistic models achieve high-quality image synthesis through novel training and lossy decompression techniques, outperforming…",
      "arxiv_url": "https://arxiv.org/abs/2006.11239",
      "authors": [
        {
          "hf_user": null,
          "hidden": false,
          "name": "Jonathan Ho"
        },
        {
          "hf_user": "ajayj",
          "hidden": false,
          "name": "Ajay Jain"
        },
        "… 1 more"
      ],
      "comments": 5,
      "github_repo": null,
      "github_stars": null,
      "id": "2006.11239",
      "media_urls": [],
      "organization": null,
      "project_page": null,
      "published_at": "2020-06-19T17:24:44.000Z",
      "submitted_by": null,
      "submitted_on_daily_at": null,
      "summary": "We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by consider…",
      "thumbnail": "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2006.11239.png",
      "title": "Denoising Diffusion Probabilistic Models",
      "upvotes": 9,
      "url": "https://huggingface.co/papers/2006.11239"
    },
    {
      "ai_keywords": [
        "denoising autoencoders",
        "diffusion models",
        "… 9 more"
      ],
      "ai_summary": "Diffusion models applied in the latent space of pretrained autoencoders with cross-attention layers achieve high-quality image synthesis wit…",
      "arxiv_url": "https://arxiv.org/abs/2112.10752",
      "authors": [
        {
          "hf_user": null,
          "hidden": false,
          "name": "Robin Rombach"
        },
        {
          "hf_user": null,
          "hidden": false,
          "name": "Andreas Blattmann"
        },
        "… 3 more"
      ],
      "comments": 5,
      "github_repo": null,
      "github_stars": null,
      "id": "2112.10752",
      "media_urls": [],
      "organization": null,
      "project_page": null,
      "published_at": "2021-12-20T18:55:25.000Z",
      "submitted_by": null,
      "submitted_on_daily_at": null,
      "summary": "By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-…",
      "thumbnail": "https://cdn-thumbnails.huggingface.co/social-thumbnails/papers/2112.10752.png",
      "title": "High-Resolution Image Synthesis with Latent Diffusion Models",
      "upvotes": 17,
      "url": "https://huggingface.co/papers/2112.10752"
    },
    "… 18 more"
  ],
  "query": "diffusion"
}

Response result

Response structure

Inferred from examples
  • cachedboolean
  • countinteger
  • credits_usedinteger
  • items(object | string)[]
    • ai_keywordsstring[]
    • ai_summarystring
    • arxiv_urlstring
    • authors(object | string)[]
      • hf_usernull | string
      • hiddenboolean
      • namestring
    • commentsinteger
    • github_reponull
    • github_starsnull
    • idstring
    • media_urlsunknown[]
    • organizationnull
    • project_pagenull
    • published_atstring
    • submitted_bynull
    • submitted_on_daily_atnull
    • summarystring
    • thumbnailstring
    • titlestring
    • upvotesinteger
    • urlstring
  • querystring

Common questions

Do I need a separate key for every provider?

Use your OpenAny API key for standard API access. Read it from OPENANY_API_KEY in your environment and keep it out of prompts, source code and logs.

Are these providers interchangeable?

No. Each offering has its own inputs, pricing and response contract. Selecting a catalog offering does not establish automatic routing or fallback. Confirm the service contract before calling.

How is this API billed?

API-key calls use your shared balance at the selected implementation's published rate. Check the billing unit and request-specific pricing rules before making a paid call. Recorded usage determines the final charge under that contract.

Where do the price and contract come from?

The selected implementation publishes its provider, request contract, revision and billing rules through OpenAny's public API catalog. A revision number identifies a contract version, not a price update date. A price update timestamp is not supplied; do not treat a page date as one.

How do OpenAny Balance and x402 differ?

OpenAny Balance uses an API key and one shared balance. Card, USDC and x402 top-ups, card auto top-up and USDC subscriptions fund that balance; available routes appear on the Credits page. Direct x402 is a separate pay-per-request flow, available only on listings that show it and requiring an authorized payment client.

Does Playground send a paid request?

Yes. After you sign in, Run sends a real API request using an active OpenAny API key. Charges follow the published API contract and use your shared balance. Selecting an implementation, editing inputs and viewing sample responses do not send requests.

Use Hugging Face paper search API with your agent

Inspect endpoint contracts and confirm availability and pricing before a paid call.