CORE Open Research Scraper
Pricing
from $1.99 / 1,000 search results
Search CORE's public open-access research index with bounded pagination, stable normalization, deduplication, safe retries, and optional proxies.
You can access the CORE Open Research Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "2.0", "x-build-id": "VFdKcB7tStrAGNEJh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/searchapi~core-open-research-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-searchapi-core-open-research-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/searchapi~core-open-research-scraper/runs": { "post": { "operationId": "runs-sync-searchapi-core-open-research-scraper", "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/searchapi~core-open-research-scraper/run-sync": { "post": { "operationId": "run-sync-searchapi-core-open-research-scraper", "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", "minLength": 1, "maxLength": 500, "type": "string", "description": "Topic, title, author, DOI, institution, or CORE query expression.", "default": "machine learning" }, "maxItems": { "title": "Maximum works", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Hard global result limit.", "default": 50 }, "maxResults": { "title": "Legacy maximum works", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Backward-compatible alias for maxItems." }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Works requested per CORE API page.", "default": 50 }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 100, "type": "integer", "description": "Hard API pagination limit.", "default": 1 }, "requestDelayMs": { "title": "Request delay", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Polite delay between pages in milliseconds.", "default": 300 }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 10, "maximum": 180, "type": "integer", "description": "Maximum seconds for one CORE request.", "default": 60 }, "maxRequestRetries": { "title": "Request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for temporary network, rate-limit, and server failures.", "default": 2 }, "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Route requests through an authorized Apify Proxy configuration.", "default": false }, "proxyGroups": { "title": "Apify Proxy groups", "type": "array", "description": "Optional authorized Apify Proxy groups.", "items": { "type": "string" }, "default": [] }, "proxyCountryCode": { "title": "Proxy country", "minLength": 2, "maxLength": 2, "type": "string", "description": "Optional two-letter country code." }, "proxyUrls": { "title": "Custom proxy URLs", "type": "array", "description": "Optional HTTP(S) proxy URLs; credentials are never logged or stored.", "items": { "type": "string" }, "default": [] } } }, "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 } } }, "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 } } } } } } } } }}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 CORE Open Research Scraper 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: