Use AgentRouter to fetch pages, scrape content, extract fields, crawl sites, map URLs, and capture screenshots across multiple providers through one API.
7
Live Providers
17
Live Routes
8 credits ($0.008)
Scrape Starts At
8 credits ($0.008)
Extract Starts At
The live web catalog currently exposes 10 capabilities for AI agents. Scrape Starts At currently starts at 8 credits ($0.008), and extract starts at currently starts at 8 credits ($0.008).
Availability Note
17 web routes are live now. The only temporary gap in the current staged surface is `web.scrape.abstract-web-scraping.mpp`.
What Is Web Crawl & Extraction?
Agent web retrieval is the operational layer that lets an AI agent fetch, scrape, extract, crawl, browse, and screenshot public websites programmatically. In production, that means the agent can move from a single page pull into multi-page exploration and structured extraction without swapping integrations mid-workflow.
Direct provider integrations usually split these jobs across different stacks. One provider may be better for raw fetch, another for clean scrape, another for structured extraction, and another for browser sessions or screenshots. That fragmentation makes routing brittle and expensive when requirements change.
AgentRouter keeps those workflows behind one routed web domain. The agent can recommend a route before execution, compare current prices, and move from fetch to scrape to extract or crawl without rebuilding the integration every time provider supply changes.
Top Scenarios
Normalize one page into readable content before the agent summarizes or stores the result.
Diffbot
MPP
8 credits ($0.008)
Firecrawl
MPP
8 credits ($0.008)
Oxylabs
MPP
8 credits ($0.008)
Docs ingestion, research agents, and one-page retrieval
Coverage: 1 capabilities · 3 live routes
Start with Page Scrape
Pull known fields directly from a page when the workflow already knows what the agent needs back.
Diffbot
MPP
8 credits ($0.008)
Firecrawl
MPP
8 credits ($0.008)
Parallel
MPP
8 credits ($0.008)
Lead capture, pricing extraction, and structured page parsing
Coverage: 1 capabilities · 4 live routes
Start with Structured Extract
Start broad with URL inventory or bounded crawl before choosing the subset of pages to process deeply.
Firecrawl
MPP
8 credits ($0.008)
Tavily
MPP
8 credits ($0.008)
Docs mirrors, site indexing, and content discovery
Coverage: 2 capabilities · 4 live routes
Use browser tooling when the agent needs a visual capture or a stateful page interaction path.
Browserbase
MPP
8 credits ($0.008)
ScreenshotOne
MPP
8 credits ($0.008)
Stateful workflows, QA agents, and visual verification
Coverage: 5 capabilities · 5 live routes
Provider Comparison
The rows below are derived from the live route catalog currently exposed through AgentRouter.
| Provider | Best For | Key Capabilities | Starting Price | Available Via |
|---|---|---|---|---|
Browserbase Covers Page Fetch, Browser Session Create, Browser Session Status, Browser Session Extend through the live routed catalog. 5 live routes | Page Fetch and Browser Session Create | Page Fetch, Browser Session Create, Browser Session Status, Browser Session Extend +1 more Modes: Managed | 8 credits ($0.008) | MPP |
Diffbot Covers Page Scrape, Structured Extract through the live routed catalog. 2 live routes | Page Scrape and Structured Extract |
Quick Start
Get an API key, ask AgentRouter to recommend the best route for the job, and execute through one shared wallet instead of wiring each provider separately.
Step 1
Enable the API once
Create one AgentRouter API key that can be reused across all live domains and capabilities.
Step 2
Recommend the route
Let AgentRouter compare the current routes, prices, and route availability before the first execute call.
Step 3
Execute the capability
Run the selected workflow through the chosen route while AgentRouter handles pricing, wallet debits, and upstream settlement.
Works with
Pricing By Task
These examples translate the current live route prices into workflow questions operators usually evaluate before shipping a domain into an agent.
| Task | Route | Price | Notes |
|---|---|---|---|
| Fetch one public page | Browserbase (web.fetch.browserbase.mpp) | 8 credits ($0.008) | Use when the agent needs raw HTTP payload and headers. |
| Scrape one docs page | Diffbot (web.scrape.diffbot.mpp) | 8 credits ($0.008) | Return clean readable content instead of raw fetch output. |
| Extract known fields | Diffbot (web.extract.diffbot.mpp) | 8 credits ($0.008) | Best when the target schema is already known. |
| Map a site before crawling | Firecrawl (web.map.firecrawl.mpp) | 8 credits ($0.008) | Inventory site URLs before spending crawl credits. |
| Capture one screenshot | ScreenshotOne (web.screenshot.screenshotone.mpp) | 8 credits ($0.008) | Return a visual artifact instead of text extraction. |
Why AgentRouter
Recommendation happens before execution, so the agent can compare current route supply and pricing instead of hard-coding one provider forever. The same routed contract stays stable even as provider coverage or transport paths change underneath.
FAQ
Agent web retrieval is the layer that lets an AI agent fetch, scrape, extract, crawl, map, browse, and screenshot public pages through one routed API domain.
Use fetch when you need the raw HTTP response, headers, or body. Use scrape when you want the page normalized into readable content.
Use extract when the agent already knows which fields it needs from one page. Use crawl when the task spans multiple pages from one starting URL.
No. AgentRouter lets the agent compare and execute the eligible live routes through one wallet and one routed API surface.
Reference
Use the capability browser below when you want contract-level detail: endpoints, live example modals, route breakdowns, and exact route prices.
| Capability | Endpoints | Price |
|---|---|---|
fetch Fetch a public page and return normalized content plus metadata. | GET /api/agentic-api/domains/web/capabilities/fetchRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/fetch/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/fetch/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. | ||
scrape Scrape one public URL and return normalized page content. | GET /api/agentic-api/domains/web/capabilities/scrapeRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/scrape/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/scrape/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. 1 route in this breakdown are temporarily unavailable. | ||
extract Extract structured data from a public URL or page input. | GET /api/agentic-api/domains/web/capabilities/extractRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/extract/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/extract/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. | ||
crawl Crawl a website from a starting URL and return pages or extracted items. | GET /api/agentic-api/domains/web/capabilities/crawlRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/crawl/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/crawl/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. | ||
map Map a website into a URL inventory without requiring full extraction of every page. | GET /api/agentic-api/domains/web/capabilities/mapRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/map/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/map/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. | ||
browser.session.create Create a browser session for stateful web interaction. | GET /api/agentic-api/domains/web/capabilities/browser-session-createRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/browser-session-create/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/browser-session-create/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. | ||
browser.session.status Get browser-session status. | GET /api/agentic-api/domains/web/capabilities/browser-session-statusRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/browser-session-status/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/browser-session-status/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. | ||
browser.session.extend Add more time to an existing browser session. | GET /api/agentic-api/domains/web/capabilities/browser-session-extendRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/browser-session-extend/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/browser-session-extend/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. | ||
browser.session.terminate Terminate an existing browser session. | GET /api/agentic-api/domains/web/capabilities/browser-session-terminateRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/browser-session-terminate/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/browser-session-terminate/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. | ||
screenshot Capture a screenshot of a public page. | GET /api/agentic-api/domains/web/capabilities/screenshotRead the capability contract, current lifecycle status, and machine-readable metadata for this web retrieval workflow. | Free |
POST /api/agentic-api/domains/web/capabilities/screenshot/recommendAsk AgentRouter to compare eligible routes inside this capability and return the best recommendation before execution. | Free | |
POST /api/agentic-api/domains/web/capabilities/screenshot/executeExecute this capability through the selected route while AgentRouter handles pricing, wallet debits, and upstream settlement. |
Related Pages
AgentRouter landing page
Browse all live domains, top API cards, and route coverage across the platform.
Install and auth
Enable AgentRouter, create the API key, and connect the shared wallet flow.
Phone, SMS & Voice domain
Create managed phone agents, provision numbers, inspect conversations and calls, and keep telephony workflows behind one supplier-neutral phone domain.
Search & Answer Engines domain
Search the public web, news, images, videos, answer engines, and multi-hop research routes through one domain.
Modes: Managed
8 credits ($0.008) |
| MPP |
Firecrawl Covers Page Scrape, Structured Extract, Site Crawl, Site Map through the live routed catalog. 4 live routes | Page Scrape and Structured Extract | Page Scrape, Structured Extract, Site Crawl, Site Map Modes: Managed | 8 credits ($0.008) | MPP |
Oxylabs Covers Page Scrape through the live routed catalog. 1 live routes | Page Scrape | Page Scrape Modes: Managed | 8 credits ($0.008) | MPP |
P Parallel Covers Structured Extract through the live routed catalog. 1 live routes | Structured Extract | Structured Extract Modes: Managed | 8 credits ($0.008) | MPP |
ScreenshotOne Covers Screenshot through the live routed catalog. 1 live routes | Screenshot | Screenshot Modes: Managed | 8 credits ($0.008) | MPP |
T Tavily Covers Structured Extract, Site Crawl, Site Map through the live routed catalog. 3 live routes | Structured Extract and Site Crawl | Structured Extract, Site Crawl, Site Map Modes: Managed | 8 credits ($0.008) | MPP |
Pricing note: 1000 credits = $1 USD. Raw API responses still return numeric credit fields such as creditsCharged.