diffbot_x_extract-analyze $0.001495 per call
Auto-detect a page type and extract it by URL. Automatically identifies the type of page being processed and routes it through the relevant Diffbot API (Diffbot · Open web & SEO data)
For AI agents: call diffbot_x_extract-analyze
POST https://toll402.dev/v1/p/diffbot.x.extract-analyze
{
"url": "https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/",
"discussion": true,
"timeout": 30000
}Answers 402 with x402 payment requirements; pay with any x402 client (@x402/fetch, x402 for Python, toll402-client, toll402-mcp) or send a prepaid-credits key as x-toll402-key (https://toll402.dev/credits). Paid per call via x402 (USDC on Base) or with a prepaid-credits key (x-toll402-key, card at /credits); charged only on success. Start at /llms.txt or connect the MCP server:
npx -y toll402-mcp · remote https://toll402.dev/mcp.Input schema
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "target URL to extract, URL-encoded",
"examples": [
"https://www.technologyreview.com/2020/09/04/1008156/knowledge-graph-ai-reads-web-machine-learning-natural-language-processing/"
]
},
"mode": {
"type": "string",
"description": "restrict extraction to one page type: article, product, discussion, image, video, list, event"
},
"fallback": {
"type": "string",
"description": "which API to fall back to if page type cannot be determined"
},
"fields": {
"type": "string",
"description": "comma-delimited optional fields: links, extlinks, meta, querystring, breadcrumb"
},
"discussion": {
"type": "boolean",
"description": "pass false to disable automatic comment/review extraction",
"examples": [
true
]
},
"timeout": {
"type": "integer",
"description": "ms to wait for content retrieval",
"examples": [
30000
]
},
"proxy": {
"type": "string",
"description": "custom proxy IP for fetching the target page"
},
"proxyAuth": {
"type": "string",
"description": "username:password for the custom proxy"
},
"useProxy": {
"type": "string",
"description": "'default' routes through Diffbot's datacenter proxy (2 credits/page instead of 1); 'none' disables proxies"
},
"renderDelay": {
"type": "integer",
"description": "extra rendering ms before DOM extraction, max 180000"
},
"scroll": {
"type": "string",
"description": "'slow' or 'fast' — triggers lazy-loaded content"
},
"callback": {
"type": "string",
"description": "JSONP callback for cross-domain AJAX"
}
},
"additionalProperties": true,
"required": [
"url"
],
"description": "different HOST than base_url — api.diffbot.com, not kg.diffbot.com"
}
MCP
{"mcpServers":{"toll402":{"command":"npx","args":["-y","toll402-mcp"],"env":{"TOLL402_WALLET_KEY":"0x..."}}}}