Scraping API cost at scale: estimate monthly credits for 500,000 requests
Most scraping API quotes fall apart at volume. The headline price per 1,000 requests is for the cheapest kind of request. The kind you actually send, a rendered page through a premium proxy, is often billed at a multiple. This guide estimates a monthly bill for 500,000 requests and shows where the estimate usually goes wrong.
Step 1: count requests, not pages
- Daily checks of 5,000 product pages: about 150,000 requests a month.
- Hourly checks of 700 pages: about 500,000 requests a month (700 × 24 × 30 = 504,000).
- Retries count only if your provider charges for them. Here, failed requests, timeouts and blocks are free.
Step 2: find the multiplier
On UnblockingAPI there is no multiplier. One successful request is one credit, with JavaScript rendering, premium proxies, country routing and retries included on every plan.
Our comparison pages put a rendered, premium-proxy request at 25 credits on ScrapingBee and ScraperAPI. At that rate, 500,000 requests would use 12.5 million credits there. Check their current pricing before you decide.
Step 3: price the credits
| Plan | Price | Credits | Per 1,000 | Concurrency |
|---|---|---|---|---|
| Scout | €49 / month | 55,000 | €0.89 | 10 |
| Builder | €199 / month | 250,000 | €0.80 | 25 |
| Growth | €499 / month | 700,000 | €0.71 | 50 |
For 500,000 requests there are two routes:
- Growth, €499 a month. 700,000 credits, so about 200,000 of headroom, plus 50 concurrent requests and 365 days of logs.
- Builder plus top-up packs. Builder's 250,000 credits for €199, then 250,000 more from packs. Cheaper than Growth at exactly 500,000, but 25 concurrent requests, 90 days of logs and no headroom unless you buy more packs.
Pay as you Go at €1.00 per 1,000 would be about €500 with 5 concurrent requests. Yearly billing saves 17%. Prices exclude VAT. Current prices are on the pricing page.
Step 4: leave headroom
- Traffic you did not plan for. Budget 20 to 30% above your estimate.
- Concurrency. If a run must finish in a fixed window, check the plan's concurrency. Enterprise has unlimited concurrency and dedicated capacity.
- Difficult targets. Run a few hundred requests per target before you scale and measure the success rate yourself.
A worked example
A team watches 700 product pages and checks each one every hour.
- Requests: 504,000 a month, so about 504,000 credits.
- Plan: Growth, €499 a month, 700,000 credits.
- Cost per successful request at full use: about €0.001.
- Headroom: about 196,000 credits.
Try it on your own targets
New accounts get 500 free credits with no card. Send a few hundred requests to the sites you care about and multiply the credits used by your monthly volume. See pricing or read the docs.
Know your bill before you scale.
Test the fetching layer before building your parser. Start with 500 free credits and no credit card. See pricing for plan details.
One successful request is one credit. No multipliers for rendering, proxies or retries.
Related guidesBrowse all guides
How to scrape public property listing pages
Fetch JavaScript-rendered property listing pages with country-level routing and parse the returned HTML.
How to scrape e-commerce product pages and pricing data
Fetch public product pages through UnblockingAPI, parse pricing and product details from the returned HTML.
How to scrape JavaScript-rendered pages
Use real browser rendering to fetch pages that load content dynamically through client-side JavaScript.
Bulk domain rating checker: Ahrefs DR for hundreds of domains
Check Ahrefs Domain Rating, backlinks and linking websites for a list of domains with one API call each - curl, Python, CSV export and daily DR tracking.
How to give your AI app live web data
Build a fetch tool for your agent, clean pages for the model and keep RAG sources fresh with rendered, unblocked page fetches.
Connect your AI agent framework to the live web over MCP
Give agents built with the Vercel AI SDK, LangChain or the Claude API a real browser through UnblockingAPI's hosted MCP server.