Agent & Infrastructure

Probe any public URL and report if it is an x402 paywall - price, network, payTo, scheme. Shop paywalls before you spend. Try GET /probe/sample.

Fresh operational audit of any public agent or paid API: reachability, latency, HTTP status, x402 challenge, price/network/payTo, OpenAPI, agent card and MCP manifest. Returns a 0-100 score, verdict and issues. Try GET /agent-health/sample.

Highest-demand x402 services tagged 'evidence': ranked by 30-day unique paying wallets, with calls, price, network and calls-per-payer for each. 743 providers and 765 paying wallets measured in this tag.

Paid MCP endpoint — POST a JSON-RPC tools/call. Tools: get_content / refresh_content (public profile data: github, twitter, linkedin) and the rep_* wallet-reputation tools (rep_rank, rep_rank_batch, rep_achievements, rep_persona_match, rep_profile_report). Flat USD prices per call, quoted in the 402.

Highest-demand x402 services tagged 'analytics': ranked by 30-day unique paying wallets, with calls, price, network and calls-per-payer for each. 128 providers and 396 paying wallets measured in this tag.

AgentWorld Paid Job Board — open jobs with rewards, required skills, categories; external agents can discover and apply

GPT Mini API - pay per call, no API key. OpenAI-format chat completions on openai/gpt-5.4-mini, pinned to OpenAI's own OpenRouter endpoint for reliability. You sign a fixed price computed from your max_tokens; unused tokens are not refunded. 20s server-side timeout - never charged if it fires; set your client timeout to 30s. Try GET /llm/gpt-mini/sample.

Generate a built-in k6 smoke/load-test script from OpenAPI 3.x without executing the target API

Returns a full decision journal entry — directional_bias, calibrated_confidence, anomaly_score, and agreement_score — plus a decision_id, combining signal, anomaly, and calibration checks into one auditable record for agent decision pipelines. Typical agent tasks: log a BTC or ETH market call for later audit, get a calibrated confidence score instead of raw output, or verify signal agreement before acting. Chain with /api/kronos/audit to verify the outcome.

Runs any read-only contract call (eth_call) with your own calldata and returns the raw result, on five chains, with no API key and no rate limit. The escape hatch for anything the typed endpoints do not cover.

Compare x402 prices before you pay. Live multi-URL quote board for AI agents: probe up to 8 Bazaar/paid API endpoints in parallel, read payment requirements (price, payTo, network), rank cheapest and fastest valid sellers, filter by budget. Agent procurement and shopping for micropayments on Base. Does not pay candidates or settle to sellers. $0.01 USDC per sheet.

Should I pay this x402 endpoint? Pre-payment honesty check for AI agents: live-probe any resource URL for a valid 402 Payment Required challenge, match payTo and budget, return allow/caution/block with signals. Bazaar seller readiness before spend. Not post-payment delivery proof. $0.005 USDC on Base.

FDA adverse event reports (FAERS) for a drug from openFDA, newest first: report id, date received, seriousness (death, hospitalisation, life-threatening), reactions, drugs taken and indication. ?q=metformin; 5 by default, up to 25 with &limit=. Cached for up to 24 hours. Reports are not proof the drug caused the event.

FDA food recalls (enforcement reports) from openFDA, newest first: matches product, firm or reason. Each recall has its number, class (I-III), status, reason, firm, dates, distribution and quantity. ?q=listeria; 10 by default, up to 25 with &limit=. Answers are cached for up to 24 hours.

FDA drug recalls (enforcement reports) from openFDA, newest first: matches product, firm, reason, brand or generic name. Each recall has its number, class (I-III), status, reason, firm, dates, distribution and quantity. ?q=valsartan; 10 by default, up to 25 with &limit=. Answers are cached for up to 24 hours.

x402 Doctor checkup of your own endpoint: payment request, prices, payTo and response time; once you prove you own the host (publish the token from /v1/doctor/verify at /.well-known/x402-doctor.txt), also a leak check: does it serve data without payment.

Check a captured x402 402 for indexing and payment blockers — no fetch

Machine-readable status and age checks for every live market, sentiment and validation source used by the Edge Agents market layer. Purpose: Let machine buyers verify whether current market evidence is fresh enough for downstream use. 5-minute freshness target; missing evidence is reported explicitly rather than invented.

Monexus Terminal API — Latest wire items. Params: category, q, limit (<=100).

LLM inference (Llama-3.1-8B via Cloudflare Workers AI). POST { prompt, system? } → { response, model }.

A paid sandbox for x402 clients. Pay $0.10 and receive your own settled payment back — payer address, amount, network and settlement transaction — so a test can assert your 402, sign, retry and settle loop works against a live facilitator. Scenario parameters exercise the failure paths for free: prove your max-price guard fires, that you abandon an expired quote, handle a rejected payment, and retry a failed settlement.

Universal agent HTTP proxy: GET|POST /api/http with url (+ optional method/headers/body) → status, filtered headers, body text|base64; SSRF-safe; $0.01 for volume (fetch remains $0.02 clean-text)

Get posts from a company's LinkedIn page. Pagination billing: call the first page normally and save billing.requestId from the Orthogonal /v1/run response. For later page, offset, or cursor calls on the same logical search, pass parentRequestId with unchanged non-pagination parameters. Valid continuation calls still get their own request IDs and quoted price, but are charged 0. Changing filters starts a new billable request.

SYNTHORA LLM Gateway SMART: OpenAI-compatible /v1/chat/completions pay-per-call, no API keys. Large free-tier models (llama-3.3-70b class) with automatic upstream failover, Ed25519-signed. 0.005 USDC via x402 on Base. POST {"messages":[{"role":"user","content":"..."}]} (or {"prompt":"..."}).