OpenReview search API

Use the OpenReview search API to retrieve matching papers, public reviews or comments and their source references. Search paper fields or switch to reviews and comments, optionally narrow venue identifiers, then use offset pagination within the first 10,000 matches to retrieve the relevant record type. Locate relevant conversations, inspect participant feedback, or retain links to a topic when investigating a technical question. Public thread visibility and the amount of message content depend on the selected endpoint and source page. 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, e.g. `diffusion models`.
Optional parameters (13)
Search in `all` fields (default), `title`, `abstract`, `authors`, `authorids`, `keywords`, `review` or `comment`.
`forum` papers (default), `reply` reviews and comments, or `all`.
`terms` (default) or `prefix` (words starting with the query).
Only notes of this venue (venue id), e.g. `ICLR.cc/2025/Conference`.
Only papers whose final venue id is this, e.g. `ICLR.cc/2025/Conference` for accepted ICLR 2025 papers.
Only papers with this venue label, e.g. `ICLR 2025 Poster`, `NeurIPS 2024 oral`.
Results per page (1-100, default 25).
Results to skip (paging).
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": 10,
  "credits_used": 1,
  "field": "all",
  "next_offset": 10,
  "query": "diffusion models",
  "results": [
    {
      "abstract": "Diffusion models have significantly advanced the field of image synthesis, making the protection of their intellectual property (IP) a criti…",
      "author_ids": [
        "~Pengzhen_Chen2"
      ],
      "authors": [
        "Pengzhen Chen"
      ],
      "authors_total": 1,
      "bibtex": null,
      "code": null,
      "content": {
        "abstract": "Diffusion models have significantly advanced the field of image synthesis, making the protection of their intellectual property (IP) a criti…",
        "authorids": [
          "~Pengzhen_Chen2"
        ],
        "authors": [
          "Pengzhen Chen"
        ],
        "html": "https://openaccess.thecvf.com/content/ICCV2025/papers/Chen_PlugMark_A_Plug-in_Zero-Watermarking_Framework_for_Diffusion_Models_ICCV_2025_pap…",
        "paperhash": "chen|plugmark_a_plugin_zerowatermarking_framework_for_diffusion_models",
        "title": "PlugMark: A Plug-in Zero-Watermarking Framework for Diffusion Models",
        "venue": "watermarking, diffusion models",
        "venueid": "OpenReview.net/Archive"
      },
      "created": "2025-11-15T14:06:00.514Z",
      "domain": "OpenReview.net/Archive",
      "forum": "6K1wTmV7E8",
      "id": "6K1wTmV7E8",
      "invitation": "OpenReview.net/Archive/-/Direct_Upload",
      "keywords": [],
      "kind": "paper",
      "license": "CC BY 4.0",
      "modified": "2025-11-15T14:06:00.514Z",
      "number": 41409,
      "pdf_url": null,
      "primary_area": null,
      "published": "2025-10-24T10:00:00.000Z",
      "supplementary_material_url": null,
      "title": "PlugMark: A Plug-in Zero-Watermarking Framework for Diffusion Models",
      "tldr": null,
      "url": "https://openreview.net/forum?id=6K1wTmV7E8",
      "venue": "watermarking, diffusion models",
      "venue_id": "OpenReview.net/Archive"
    },
    {
      "abstract": "In Diffusion Probabilistic Models (DPMs), the task of modeling the score evolution via a single time-dependent neural network necessitates e…",
      "author_ids": [
        "~Etrit_Haxholli1",
        "~Marco_Lorenzi1"
      ],
      "authors": [
        "Etrit Haxholli",
        "Marco Lorenzi"
      ],
      "authors_total": 2,
      "bibtex": null,
      "code": null,
      "content": {
        "abstract": "In Diffusion Probabilistic Models (DPMs), the task of modeling the score evolution via a single time-dependent neural network necessitates e…",
        "authorids": [
          "~Etrit_Haxholli1",
          "~Marco_Lorenzi1"
        ],
        "authors": [
          "Etrit Haxholli",
          "Marco Lorenzi"
        ],
        "html": "https://neurips.cc/virtual/2023/workshop/66539",
        "paperhash": "haxholli|faster_training_of_diffusion_models_and_improved_density_estimation_via_parallel_score_matching",
        "pdf": "/pdf/16b9aa7a2f7f0f741a7b795441b995c1be1b02b0.pdf",
        "title": "Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matching",
        "venue": "NeurIPS 2023 Workshop on Diffusion Models",
        "venueid": "OpenReview.net/Archive"
      },
      "created": "2024-08-15T07:52:52.615Z",
      "domain": "OpenReview.net/Archive",
      "forum": "SavXSnly6h",
      "id": "SavXSnly6h",
      "invitation": "OpenReview.net/Archive/-/Direct_Upload",
      "keywords": [],
      "kind": "paper",
      "license": "CC BY 4.0",
      "modified": "2024-08-15T07:52:52.615Z",
      "number": 27700,
      "pdf_url": "https://openreview.net/pdf/16b9aa7a2f7f0f741a7b795441b995c1be1b02b0.pdf",
      "primary_area": null,
      "published": "2023-12-15T08:51:36.854Z",
      "supplementary_material_url": null,
      "title": "Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matching",
      "tldr": null,
      "url": "https://openreview.net/forum?id=SavXSnly6h",
      "venue": "NeurIPS 2023 Workshop on Diffusion Models",
      "venue_id": "OpenReview.net/Archive"
    },
    "… 8 more"
  ],
  "source": "forum",
  "total": 10000
}

Response result

Response structure

Inferred from examples
  • cachedboolean
  • countinteger
  • credits_usedinteger
  • fieldstring
  • next_offsetinteger
  • querystring
  • results(object | string)[]
    • abstractstring
    • author_idsstring[]
    • authorsstring[]
    • authors_totalinteger
    • bibtexnull
    • codenull
    • contentobject
      • abstractstring
      • authoridsstring[]
      • authorsstring[]
      • htmlstring
      • paperhashstring
      • titlestring
      • venuestring
      • venueidstring
      • pdfstring
    • createdstring
    • domainstring
    • forumstring
    • idstring
    • invitationstring
    • keywordsunknown[]
    • kindstring
    • licensestring
    • modifiedstring
    • numberinteger
    • pdf_urlnull | string
    • primary_areanull
    • publishedstring
    • supplementary_material_urlnull
    • titlestring
    • tldrnull
    • urlstring
    • venuestring
    • venue_idstring
  • sourcestring
  • totalinteger

Loading related APIs…

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 OpenReview search API with your agent

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