Grounded honey recommendations: send a flavor/use/occasion intent, receive ranked varieties chosen from Melvea's proprietary flavor, terroir, and scoring corpus — each with a grounded reason. Recommends on taste and use, not health.

Use this when you already suspect two specific carriers (by USDOT number) are the same operation under different paper and want it confirmed, without receiving any information about a carrier you didn't name. Returns only linked true/false and, when true, the shared cluster_id — never a member list. Billed whenever both USDOT numbers resolve, whether or not they turn out to be linked; supplying the same number twice is free.

$0.005/image. Detect protective equipment — face, hand, head covers — on people in an image. Site-safety audits by API. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny

Settlement assurance for a completed x402 payment on Base or Solana: confirm the transaction succeeded (0x hash or base58 signature), match the USDC transfer to an expected wallet and amount, format a receipt, and optionally audit the issuing endpoint - as one 0-100 scored report with a verdict.

Compare any two NFT collections on the full due-diligence metric set: supply, holders, holder ratio, top-10 concentration, wash-trading score and activity trend — with a winner per metric. The head-to-head an agent runs before recommending one collection over another. Use this when an agent needs to two collections side-by-side, metric by metric verdicts.

RugRadar Watch + Alert: watch one Solana token (pump.fun incl.) for 24h ($0.05) or 48h ($0.10). Re-checked about every 10 min; signed webhook alert when the dev sells, liquidity drops 30%+, mint/freeze authority appears, risk score jumps 20+ points, or it can't be sold. Heuristic, may be wrong. Not financial advice.

Scan a URL for phishing or malware using heuristic signals (Google Safe Browsing, RDAP domain age, known IOC corpus) plus VirusTotal multi-engine analysis. Returns an async analysis ID to poll. Call before an agent clicks, fetches, or shares a link from an untrusted source.

Top 100 recent AI papers ranked by the share of their total citations earned in the most recent calendar year. Papers published in the last 2 years with 3+ citations. Surfaces papers that are still gaining traction now. OpenAlex CC0.

Explain what an EVM transaction would actually do: decodes the calldata (ERC-20 transfers/approvals via known ABIs, unknown selectors via the 4byte directory) and simulates the call against live chain state to report the outcome — including unlimited-approval warnings — without sending anything. Use this when an agent needs to decode and simulate a transaction — before signing it.

Decide whether an autonomous agent both can and should execute an exact x402 payment. Verifies predelegated spending authority, challenge/request integrity, and public merchant transaction-risk signals, then returns an evidence-based APPROVED, REVIEW or DENIED clearance plus a signed clearance token. APPROVED means the agent may proceed autonomously; REVIEW means do not auto-pay until higher-level review; DENIED means do not pay.

$0.003/call. Render HTML to an image — sandboxed headless Chromium screenshot of your markup. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny

Fact-check numbers in Korean finance text: every checkable number (rates, KTB yields, FX, listed-company revenue and profit, % vs %p, 조/억/만 units) marked MATCH or MISMATCH against the official value with date and source (ECOS, KEXIM, DART). Numbers with no source stay unverified.

Korean rates and FX: Bank of Korea base rate, KOFR, CD, CP, KTB yields 1y-50y (ECOS) and won exchange rates (KEXIM, customs) for a date, from an English or Korean question. Official values with series id, date and source.

TikHub — 171 per-call social-data endpoints (POST) across douyin/tiktok/wechat_channels/xiaohongshu/wechat_mp/lemon8/wechat_search/bilibili & more. Pass { endpoint, ...params } (params per endpoint; most reads take username/user_id/keyword + pagination_token). Find endpoints via vaaya/discover or the social-data knowledge doc. Most calls 1¢.

Finished styling report as a PDF (language: en default | ja), rendered from the full style-profile analysis: cover, verdict summary, palette with swatches, face/frame chapters, measured strengths, outfit formulas and two virtual-draping boards built from the client photo. Deterministic rendering - identical quality every call. The returned PDF embeds the photo (kept for receipt re-fetch; see /terms). Flat $2.99/call (volume: report-pack 10 credits at $1.99/unit).

An isolated Agentify QA product. Returns a synthetic digital receipt for a Base Sepolia test purchase. No physical goods, email, subscription or real-world service.

AIOptiTech Prompt Library prompt body. Pay 0.05 USDC once for the prompt identified by the id path parameter. Personal use. An active subscription pass can read it without a second payment.

Step-by-step instructions for wrapping a rectangular box neatly: what you need, how to measure and cut the paper, how to fold the sides and the ends, and how to tie a ribbon with a bow. Delivered as one plain-text file.

Details of a mobile app on the Apple App Store or Google Play by id, package name or store URL: title, developer, developer email and website, rating, rating counts, installs, price, genre, release and update dates. Use for app research, competitor tracking or developer contact lookup.

Hosted by vAPI for o1.exchange: Get details for one tracked launch token.