Brand-safe sourcing,shipped today.
Your customers generate brand content. They can't risk a plagiarism claim. Skip the licensing deals — pay-per-query access to 1,000+ publishers with full attribution and receipts. Brand-safe inputs, in three lines of code.
The current options all suck.
Scrape and pray. Negotiate for 18 months. Or buy stale Common Crawl. Pick your poison.
Plagiarism risk on every output
Your model paraphrases scraped content. Customer publishes. Original publisher's lawyer sends a letter. Your contract has indemnification clauses.
Enterprise customers demand sourcing transparency
Your largest deal asks: "Where did the model learn this?" "Public web data" doesn't cut it for a $5M ACV contract.
Stale training data = stale outputs
Customers want copy that references this week's news, this quarter's earnings, today's product launches. Your model knows 2024.
xpay is the fourth option.
Skip the lawsuits. Skip the licensing deals. Skip the attribution headaches. Pay-per-query, one account, every publisher in our network.
Licensed, attributable inputs
Every snippet pulled into your generation pipeline is paid-for and citable. Indemnification footing changes from "hope" to "evidence."
Drop-in retriever, three lines
Add xpay✦ as a retrieval source in your existing chain — Anthropic, OpenAI, your own model. No infra rebuild.
Brand-safety filters per customer
Allow-list publishers per workspace. Enterprise customer wants only Tier-1 sources? Configure it. No code changes per tenant.
Three lines. Ship Tuesday.
Native SDKs across the agent stack. Drop in xpay where you already retrieve.
import { XpayRetriever } from '@xpay/sdk';
const retriever = new XpayRetriever({
wallet,
allowList: ['reuters.com', 'wsj.com', 'bloomberg.com'],
maxCostPerGeneration: 0.50,
});
const sources = await retriever.fetch(brief);
const draft = await llm.complete({
prompt: buildPrompt(brief, sources),
});
// draft.citations are real, paid, traceable URLs.Live in five minutes.
01
Get an API key
Sign up at app.xpay.sh, fund a wallet (USDC on Base), get your API key. New accounts ship with $50 in free credits.
02
Drop in the retriever
Three lines of code. Native SDKs for LangChain, LlamaIndex, CrewAI, Stagehand, Playwright. Or hit the REST API directly with x402 headers.
03
Get licensed content + receipts
Each query returns the document, publisher attribution, and a settlement receipt. Pay only for what you actually retrieve. Cap spend per project, per user, per domain.
Built for agents like these
AI writing platforms
Jasper, Copy.ai, Writer.com, AnywordMarketing content tools
Brand-safe content generation at scaleInternal enterprise content
F500 marketing/comms AI assistantsStop scraping.Start retrieving, legally.
One API key. 1,000+ publishers. Per-query pricing. Receipts and attribution by default.
Self-serve · $50 free credits · No BD calls · No MSA requiredAI Writing Tools — FAQ
Common questions from agent builders evaluating xpay
Outputs grounded in licensed, retrieved sources have citations. Citations create a paper trail — your customer can show "this draft was informed by these paid sources" rather than "the model invented it." Insurers and legal teams treat the two very differently.
Yes. Per-workspace configuration. Tier-1-only for the bank, broad allow for the media agency. Same code path.
Up to you. Most platforms absorb at $0.05-$0.15 per generation as part of their margin; some surface it as an "enterprise sourcing" upsell. We provide per-query receipts so you can pass-through cleanly if you choose.
Yes. xpay is the retrieval layer, not the generation layer. Compose with OpenAI, Anthropic, your own fine-tuned model — the source documents flow into your prompt as you already do RAG.
Set per-generation spend caps. xpay's retriever does intelligent re-ranking so you typically pay for 3-5 highly relevant sources, not 50.