Refinery — HTML to LLM Text (Cut RAG Token Cost)
Pricing
from $2.00 / 1,000 html extractions
HTML to LLM text cleaner for RAG pipelines. Strip scripts, nav & layout junk after Firecrawl or your fetch. BeautifulSoup-alternative speed. $0.002/page · 3 README demos in Console.
You can access the Refinery — HTML to LLM Text (Cut RAG Token Cost) programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
# Set API token$API_TOKEN=<YOUR_API_TOKEN>
# Prepare Actor input$cat > input.json << 'EOF'<{< "urls": [< "https://example.com"< ],< "raw_payload": "<html><head><script>gtag('event','page_view')</script><style>.nav,.footer{display:block}</style></head><body><nav>Home · Pricing · Login</nav><article><h1>Quarterly update</h1><p>We reduced embedding cost by cleaning HTML before chunking.</p></article><footer>© 2026 · Legal · Careers</footer></body></html>"<}<EOF
# Run the Actor using an HTTP API# See the full API reference at https://docs.apify.com/api/v2$curl "https://api.apify.com/v2/acts/larelabs~refinery-html-to-llm-cleaner/runs?token=$API_TOKEN" \< -X POST \< -d @input.json \< -H 'Content-Type: application/json'Below, you can find a list of relevant HTTP API endpoints for calling the Refinery — HTML to LLM Text (Cut RAG Token Cost) Actor. For this, you’ll need an Apify account. Replace <YOUR_API_TOKEN> in the URLs with your Apify API token, which you can find under Integrations in Apify Console. For details, see the API reference.
https://api.apify.com/v2/acts/larelabs~refinery-html-to-llm-cleaner/runs?token=<YOUR_API_TOKEN>Note: By adding the method=POST query parameter, this API endpoint can be called using a GET request and thus used in third-party webhooks. Please refer to our Run Actor API documentation.
https://api.apify.com/v2/acts/larelabs~refinery-html-to-llm-cleaner/run-sync-get-dataset-items?token=<YOUR_API_TOKEN>Note: This endpoint supports both POST and GET request methods. However, only the POST method allows you to pass input data. For more information, please refer to our Run Actor synchronously and get dataset items API documentation.
https://api.apify.com/v2/acts/larelabs~refinery-html-to-llm-cleaner?token=<YOUR_API_TOKEN>For more information, please refer to our Get Actor API documentation.
Actors can be used to scrape web pages, extract data, or automate browser tasks. Use the Refinery — HTML to LLM Text (Cut RAG Token Cost) API programmatically via the Apify API.
You can choose from:
You can start Refinery — HTML to LLM Text (Cut RAG Token Cost) with the Apify API by sending an HTTP POST request to the Run Actorendpoint. An Actor’s input and its content type can be passed as a payload of the POST request, and additional options can be specified using URL query parameters. The Refinery — HTML to LLM Text (Cut RAG Token Cost) is identified within the API by its ID, which is the creator’s username and the name of the Actor.
When the Refinery — HTML to LLM Text (Cut RAG Token Cost) run finishes you can list the data from its default dataset(storage) via the API or you can preview the data directly on Apify Console.