Academic Paper Search: OpenAlex, PubMed, arXiv
Pricing
from $1.50 / 1,000 paper returneds
Go to Apify Store
Academic Paper Search: OpenAlex, PubMed, arXiv
Pricing
from $1.50 / 1,000 paper returneds
You can access the Academic Paper Search: OpenAlex, PubMed, arXiv programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "Y82fgtHqbdvIrDhDR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/bravona~academic-papers-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-bravona-academic-papers-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/bravona~academic-papers-search/runs": { "post": { "operationId": "runs-sync-bravona-academic-papers-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/bravona~academic-papers-search/run-sync": { "post": { "operationId": "run-sync-bravona-academic-papers-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "query" ], "properties": { "query": { "title": "Search query", "type": "string", "description": "Search terms, e.g. a topic like CRISPR. Sent to each source's own search (OpenAlex search, PubMed search terms, arXiv all-fields search), so matching can vary by source. Required; no default." }, "sources": { "title": "Sources", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Databases to search: OpenAlex, PubMed, arXiv. Optional; defaults to all three. Select at least one. Searching fewer sources is faster; arXiv is the slowest because it allows one request every three seconds.", "items": { "type": "string", "enum": [ "openalex", "pubmed", "arxiv" ], "enumTitles": [ "OpenAlex", "PubMed", "arXiv" ] }, "default": [ "openalex", "pubmed", "arxiv" ] }, "fromYear": { "title": "From year", "minimum": 1000, "maximum": 2100, "type": "integer", "description": "Earliest publication year to include, e.g. 2023. Leave empty to apply no lower bound. If both years are empty, there is no year filter." }, "toYear": { "title": "To year", "minimum": 1000, "maximum": 2100, "type": "integer", "description": "Latest publication year to include, e.g. 2026. Leave empty to apply no upper bound. If both years are empty, there is no year filter." }, "maxResults": { "title": "Max results per source", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum papers to save from each selected source (1 to 10,000; default 100). With 3 sources you can get up to 3 × this number, before duplicates are merged. Each saved paper is billed at $0.0015 ($1.50 per 1,000), so this also caps cost.", "default": 100 }, "dedupe": { "title": "Remove duplicates", "type": "boolean", "description": "Merge the same paper found in several sources (matched by DOI, PMID, arXiv ID, then a careful title match) into one record. Default: on. The foundIn field lists every source that returned the paper.", "default": true }, "openAlexApiKey": { "title": "OpenAlex API key (optional)", "type": "string", "description": "Optional, recommended. A free OpenAlex key raises your daily OpenAlex budget 10× (a free key gets $1 a day) and allows cursor paging past the first page; it does not change speed (about 8 requests/s either way). Without a key, if the small daily budget runs out, the run continues with PubMed and arXiv only. Stored encrypted." }, "ncbiApiKey": { "title": "NCBI API key (optional)", "type": "string", "description": "Optional. Your NCBI key raises PubMed from 3 to 10 requests/s. Stored encrypted." }, "contactEmail": { "title": "Contact email (optional)", "type": "string", "description": "Optional. An email passed to NCBI and OpenAlex as a polite contact. Leave empty to send none." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Academic Paper Search: OpenAlex, PubMed, arXiv from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: