You can access the LLM Web Page Research Browser 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.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

{
  "openapi": "3.0.1",
  "info": {
    "version": "0.1",
    "x-build-id": "E87GaWa0dGwszcmLm"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/automation-lab~llm-web-page-research-browser/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-automation-lab-llm-web-page-research-browser",
        "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": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/automation-lab~llm-web-page-research-browser/runs": {
      "post": {
        "operationId": "runs-sync-automation-lab-llm-web-page-research-browser",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/automation-lab~llm-web-page-research-browser/run-sync": {
      "post": {
        "operationId": "run-sync-automation-lab-llm-web-page-research-browser",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$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": [
          "startUrls"
        ],
        "properties": {
          "startUrls": {
            "title": "Public page URLs",
            "minItems": 1,
            "maxItems": 50,
            "type": "array",
            "description": "Anonymous public HTTP(S) pages to process. Login-gated pages, private networks, file URLs, and browser-only applications are not supported.",
            "items": {
              "type": "object",
              "required": [
                "url"
              ],
              "properties": {
                "url": {
                  "type": "string",
                  "title": "URL of a web page",
                  "format": "uri"
                }
              }
            }
          },
          "maxPages": {
            "title": "Maximum pages",
            "minimum": 1,
            "maximum": 50,
            "type": "integer",
            "description": "Maximum number of unique supplied URLs to process in this run.",
            "default": 10
          },
          "maxContentChars": {
            "title": "Maximum content characters per page",
            "minimum": 1000,
            "maximum": 250000,
            "type": "integer",
            "description": "Truncate cleaned page content after this many characters to keep RAG payloads bounded.",
            "default": 50000
          },
          "chunkSize": {
            "title": "Chunk size",
            "minimum": 500,
            "maximum": 10000,
            "type": "integer",
            "description": "Target maximum characters in each compact Markdown chunk.",
            "default": 2000
          },
          "chunkOverlap": {
            "title": "Chunk overlap",
            "minimum": 0,
            "maximum": 2000,
            "type": "integer",
            "description": "Characters repeated between neighboring chunks. Must be smaller than chunk size.",
            "default": 200
          },
          "maxLinks": {
            "title": "Maximum same-origin links",
            "minimum": 0,
            "maximum": 500,
            "type": "integer",
            "description": "Maximum normalized same-origin links extracted from each source page.",
            "default": 100
          },
          "includeMarkdown": {
            "title": "Include Markdown",
            "type": "boolean",
            "description": "Include the complete cleaned Markdown field in each page record.",
            "default": true
          },
          "includeText": {
            "title": "Include plain text",
            "type": "boolean",
            "description": "Include a plain-text representation in addition to chunks.",
            "default": true
          },
          "requestTimeoutSecs": {
            "title": "Request timeout",
            "minimum": 5,
            "maximum": 120,
            "type": "integer",
            "description": "Maximum seconds for each HTTP request.",
            "default": 30
          },
          "maxRetries": {
            "title": "Transient retries",
            "minimum": 0,
            "maximum": 4,
            "type": "integer",
            "description": "Retries for timeouts, network failures, HTTP 429, and temporary server errors.",
            "default": 2
          }
        }
      },
      "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
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

LLM Web Scraping to Cited Markdown & Chunks OpenAPI definition

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 LLM Web Page Research Browser from the options below:

OpenAPI.json

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:

LLM Web Page Research Browser API in Python

LLM Web Page Research Browser API in JavaScript

LLM Web Page Research Browser API through CLI

LLM Web Page Research Browser API

AI Web Extractor: URL → Clean Markdown + JSON for LLM/RAG

boxbox10/ai-web-extractor

Turn any URL into clean, LLM-ready Markdown + structured JSON (title, headings, main content, links, metadata, token count). Perfect for RAG pipelines, AI agents, and LLM context.

Marvin Eguilos

URL to Markdown - Clean Web Pages for LLMs & RAG

scrapesage/url-to-markdown

Convert any list of web pages to clean Markdown for LLM/RAG ingestion, notes or docs. Main-content mode (Readability) keeps just the article; full-page mode converts the whole body. Tables and links preserved. No browser.

Scrape Sage

URL to Markdown MCP

reverberant_equality/mcp-url-to-markdown

Convert any web page to clean markdown for AI agents. Uses Firefox Reader Mode engine for content extraction. Perfect for RAG pipelines, research, and LLM content ingestion.

Jordan C

LLM-Ready Web Content Extractor

beyondxl/llm-ready-content-extractor

Turn any public web page or shallow site crawl into clean, LLM-ready Markdown + metadata + optional RAG chunks. Boilerplate/nav/ads removed. Honors robots.txt.

Leopold Ai

LLM-Ready Web Extractor

phantom_horse/my-actor-1

Turn any web page into clean, LLM-ready Markdown. Strips scripts, nav, and page chrome, then converts the main content to tidy Markdown with title, meta description, and token counts. Perfect for AI prompts and RAG ingestion pipelines.

NATNAEL FIKRE

PDF Extractor: PDF → Clean Markdown + JSON for LLM/RAG

boxbox10/pdf-extractor

Turn any PDF URL into clean, LLM-ready Markdown + structured JSON (title, metadata, per-page text, page count, word count, token count). Perfect for RAG pipelines, AI agents, and LLM document ingestion.

Marvin Eguilos

Website Content Crawler — Text, Markdown & HTML for AI/LLM

hichemdev/website-content-crawler

Crawl any website and extract clean text, Markdown, and HTML from every page — ready for LLM, RAG, and AI ingestion.

Hichem Ben Moussa

Doc to Markdown — DOCX, PDF & web pages to clean markdown

amanatools/doc-to-markdown

Convert DOCX files, PDFs, and web pages into clean markdown for LLM and agent ingestion. Main-content extraction strips navigation junk from web pages. Pay per document.

Dos

Web-to-Markdown Generator for AI & RAG Pipelines

profitstack/web-to-markdown-generator-for-ai-rag-pipelines

Convert any website into clean, heading-based chunking, LLM-ready Markdown for RAG and AI agents.

Manas Mantri

LLM-Ready Web Extractor: URL to Clean Markdown & JSON

f0rty7even/llm-web-extractor

Turn any web page or site into clean, LLM-ready Markdown and structured JSON for RAG, agents, and fine-tuning. Strips nav/ads/boilerplate; returns main content + metadata.