Add to Chrome
You need a list of companies, products, or job openings. Before choosing a tool, check whether a maintained extractor already does that job, or whether the task needs someone to navigate the site and decide what to collect.
Retriever AI lets you describe the task in your browser. Apify offers ready-made Actors as well as a platform for running your own. An Actor is a program with inputs and outputs; using an existing one does not necessarily mean writing code.
Choose by the source and the result
| Your situation | Start here |
|---|---|
| You want to collect a small list from pages open in Chrome | Try Retriever's website data workflow |
| A maintained Actor already supports the site and fields you need | Test that Actor on Apify |
| Research must continue into a form or another signed-in site | Try Retriever's document-to-form workflow |
| You need a repeatable dataset in an existing Actor pipeline | Evaluate Apify's outputs and running costs |
These are starting points, not guarantees of site access or accuracy. Check the specific source with a small sample.
Compare what the bill measures
Checked September 22, 2026: Apify's free plan includes $5 of monthly usage. Starter is $19/month plus usage beyond the included amount. Store Actors use pay-per-event or pay-per-usage pricing; compute, proxies, storage, and data transfer can affect the total. Read the selected Actor's pricing before extrapolating from a sample. Apify pricing
Retriever includes supported AI in interactive Free Mode. You do not need your own model key to start. Repeating the task on a schedule requires a subscription, and purchased data or managed proxies can add costs. The full boundary is below.
Run a useful comparison
Use the same directory and request the same 20 records: company name, website, location, and source URL. Keep missing fields blank. Check every row, record duplicates, and note the time spent fixing the output.
Then compare the total cost of the intended cadence. A good one-time export does not establish that a recurring collection will stay accurate when the source changes.
Our website collection example includes a small reference file and a prompt you can adapt. This article is a documentation review, not a new head-to-head benchmark.
Watch multi-site extraction
Collect data across websites.
A recorded multi-site extraction with parallel browser agents. This demonstrates Retriever's workflow, not a matched test against the other product.
What Retriever's free plan covers
Free Mode includes supported AI models and Cloud browser time for tasks you start in the extension or Cloud dashboard. No AI API key or paid AI subscription is required. Sponsored cards and a daily fair-use allowance apply. Your account shows the current allowance and reset time. When you reach it, wait for the reset, use your own AI provider, or choose a paid plan. Your provider may charge for its usage.
One schedule that runs once a day or less often, in the Cloud or in your Chrome, is included, paid from the daily allowance. More schedules, faster schedules, triggers, cookie sync, API runs, rtrvr's agent over MCP, and WhatsApp tasks require a paid plan. Browser tools that let your own AI drive your Chrome over MCP are free on every plan. Data enrichment and managed proxies can use credits separately. On the free plan, Cloud API calls made with an API key, the MCP Cloud tools (cloud_agent, cloud_scrape, and agent or scrape when they run in Cloud), and WhatsApp tasks need a paid plan, as does running rtrvr's agent in your Chrome through API or MCP. Free Mode covers the tasks you start in the extension or Cloud dashboard. On a paid plan, API, MCP, and WhatsApp runs use credits for the resources they consume.
Free Mode involves sponsored content in both the Chrome extension and Cloud, as described in the Terms and Privacy Notice. Compare plans, read the terms, or check the privacy notice.
