22 pay-per-call APIs for AI agents. New services and catalogue updates as they happen. https://agents.melis.ai/feed.xml 2026-05-15T21:45:08.068Z Sean Melis sean@melis.ai https://melis.ai Content licensed CC-BY-4.0; code samples MIT. https://agents.melis.ai/favicon.svg https://github.com/mizukaizen/x402-tools-mcp/raw/main/assets/logo-400.png https://agents.melis.ai 2026-05-15T00:00:00Z

Boring infrastructure for AI agents. 22 pay-per-call x402 utility APIs. No accounts, no API keys. USDC on Base.

Sean Melissean@melis.ai https://agents.melis.ai/pipelines/rag 2026-05-15T00:00:00Z

Build a secure, pay-per-call RAG pipeline using melis x402 services: ScrapePay → MarkdownOpt → EmbedPay → MemoryServe → MEMSCRUB. ~$0.017 per page.

Sean Melissean@melis.ai https://agents.melis.ai/docs/getting-started 2026-05-15T00:00:00Z

Five-minute onboarding for melis x402 Tools. Install the MCP wrapper, fund a Base wallet with $1 USDC, make your first paid scrape.

Sean Melissean@melis.ai https://agents.melis.ai/agents-faq 2026-05-15T00:00:00Z

Agent-builder FAQ — discovery surfaces, x402 payment flow, MCP integration, budget enforcement, prompt injection defence.

Sean Melissean@melis.ai https://agents.melis.ai/comparison/vs-firecrawl 2026-05-15T00:00:00Z

Honest comparison: x402 pay-per-call scraping vs account-based subscription scraping. When each wins.

Sean Melissean@melis.ai https://agents.melis.ai/comparison/vs-openai-embeddings 2026-05-15T00:00:00Z

Wrapper premium vs direct API: when the no-signup convenience is worth ~2.5× per token.

Sean Melissean@melis.ai https://agents.melis.ai/comparison/vs-pinecone 2026-05-15T00:00:00Z

Honest comparison: x402 pay-per-call agent memory vs enterprise managed vector DB.

Sean Melissean@melis.ai https://agents.melis.ai/use-cases/agent-memory 2026-05-15T00:00:00Z

Composition recipe for adding semantic memory to any agent runtime with MemoryServe + EmbedPay.

Sean Melissean@melis.ai https://agents.melis.ai/use-cases/content-moderation 2026-05-15T00:00:00Z

Three-layer moderation: PromptGuard (input) + MEMSCRUB (RAG) + ImageGuard (images). Pay per check.

Sean Melissean@melis.ai https://agents.melis.ai/compose 2026-05-15T00:00:00Z

Seven worked workflows that compose melis x402 services: safe research, notification pipeline, document generation, URL verification, RAG pipeline, content moderation, agent memory.

Sean Melissean@melis.ai https://agents.melis.ai/pricing 2026-05-15T00:00:00Z

Full price table. USDC on Base, no subscriptions, no minimum spend, charge-on-success-only.

Sean Melissean@melis.ai https://agents.melis.ai/services/scrapepay 2026-05-15T00:00:00Z

Web extraction via Playwright. Charge-on-failure-safe.

Pay-per-call web scraping via headless Playwright. Returns page content as text, HTML, or markdown. Enforces robots.txt before settling payment — if the page disallows crawling, you get a 451 and no charge. SSRF-hardened: private IP ranges and Hetzner metadata endpoints are blocked. Payment only settles on 2xx response with non-empty content. Sean Melissean@melis.ai https://agents.melis.ai/services/markdownopt 2026-05-15T00:00:00Z

URL or HTML → clean LLM-ready markdown. ~70% token reduction.

Pass a URL or raw HTML; receive back clean markdown stripped of nav, footers, ads, and boilerplate. Returns a token estimate for both the original HTML and the cleaned output. Typical reduction is ~70%. Use this as your default "fetch and read" step before passing web content to an LLM — it costs $0.005 and saves far more in LLM token spend. Sean Melissean@melis.ai https://agents.melis.ai/services/structextract 2026-05-15T00:00:00Z

HTML → structured JSON. Tables, links, emails, phones, headings.

Takes raw HTML and returns clean structured JSON with the data you actually need — tables, links, email addresses, phone numbers, headings, meta tags, and images. Pass raw ScrapePay HTML output through StructExtract before giving it to an LLM. You'll get precise extracted fields instead of asking the LLM to parse markup. Sean Melissean@melis.ai https://agents.melis.ai/services/cacheserve 2026-05-15T00:00:00Z

Fetch a URL with server-side caching. Avoid redundant requests.

Fetches a URL and caches the response server-side. If the same URL has been fetched within the TTL window, returns the cached version without hitting the origin. Useful when multiple agents in a workflow might need the same page, or when you want to avoid hammering a server with repeated requests. Cache miss cost: $0.001. Cache hit cost: $0.001 (charged on served request regardless). Sean Melissean@melis.ai https://agents.melis.ai/services/linkrisk 2026-05-15T00:00:00Z

Lightweight URL risk profile. Heuristic, fast, cheap.

Profiles an external URL before your agent visits or acts on it. Returns a risk score (0–100), risk level (low/medium/high), flags (phishing signals, suspicious TLD, URL shortener, etc.), redirect chain, and final resolved URL. Faster and cheaper than LinkSafe — use this as your first-pass filter. Escalate to LinkSafe only when you need a definitive sandbox verdict. Sean Melissean@melis.ai https://agents.melis.ai/services/linksafe 2026-05-15T00:00:00Z

Definitive URL safety verdict. Playwright sandbox + VirusTotal.

Full safety check for URLs your agent is about to share with a user or embed in content. Runs a Playwright headless browser sandbox, checks VirusTotal, and traces the full redirect chain. Returns a binary safe/unsafe verdict, a risk score, and a list of specific threats found. Heavier than LinkRisk — use LinkRisk for quick profiling and LinkSafe when you need the authoritative verdict. Sean Melissean@melis.ai https://agents.melis.ai/services/promptguard 2026-05-15T00:00:00Z

Score untrusted input for prompt injection risk.

Takes any user-supplied string and returns a prompt injection risk score from 0 to 100, a risk level (low/medium/high), and a list of specific flags (jailbreak attempt, instruction override, role-play injection, etc.). Use this before passing any untrusted external input to an LLM or routing it to a tool. If safe: false, reject and warn. Sean Melissean@melis.ai https://agents.melis.ai/services/schemagate 2026-05-15T00:00:00Z

Validate LLM output against JSON Schema before passing downstream.

Post an LLM output string and a JSON Schema; receive a binary valid/invalid verdict plus a hint describing the validation failure. Use this as the last step before treating LLM output as structured data. Prevents downstream type errors, broken pipelines, and hallucinated field names from propagating. Sean Melissean@melis.ai https://agents.melis.ai/services/docconvert-text 2026-05-15T00:00:00Z

Format conversion: md↔html, html↔txt, json↔csv.

Convert document content between formats. Supported conversions: md→html, md→txt, html→md, html→txt, json→csv, csv→json. Returns the converted content and size in bytes. Use this as a preprocessing step when your pipeline receives content in one format but needs it in another before the next tool call. Sean Melissean@melis.ai https://agents.melis.ai/services/docconvert-pdf 2026-05-15T00:00:00Z

HTML or markdown → PDF. Base64 output.

Converts HTML or markdown content to a PDF via headless Playwright. Returns the PDF as a base64-encoded string. Use when an agent's output should be a downloadable document — reports, invoices, formatted summaries. Not a default step in most pipelines; use it explicitly when PDF is the right output format. Sean Melissean@melis.ai https://agents.melis.ai/services/notifyrelay-email 2026-05-15T00:00:00Z

Send a transactional email from your agent. $0.005.

Sends a transactional email via Resend from within an agent task. Requires to, subject, and body fields. Rate-limited at 10 requests per minute per IP. Allowlisted sender domains only. Use when an agent needs to alert a human, deliver a report, or confirm an action. Sean Melissean@melis.ai https://agents.melis.ai/services/notifyrelay-telegram 2026-05-15T00:00:00Z

Send a Telegram message from your agent. $0.002.

Sends a Telegram message to a known chat ID. Supports Markdown formatting. Use for agent-to-human notifications where Telegram is the preferred channel. Cheaper than email — use this for frequent status updates, use email for formal delivery. Sean Melissean@melis.ai https://agents.melis.ai/services/notifyrelay-webhook 2026-05-15T00:00:00Z

POST JSON to any public URL. Optional HMAC signing. $0.001.

Posts a JSON payload to any public external URL. Supports optional HMAC-SHA256 signing via a shared secret. The signed hash is attached as X-Hub-Signature-256, matching the GitHub/Stripe webhook convention. SSRF-protected — private IP ranges and metadata endpoints are blocked. Use for integrating with Zapier, Make, IFTTT, or any webhook-based automation. Sean Melissean@melis.ai https://agents.melis.ai/services/pdf-render 2026-05-15T00:00:00Z

High-fidelity URL or HTML → PDF via Playwright. $0.49.

Renders a public URL or raw HTML to a high-fidelity PDF using Playwright. Handles CSS, fonts, and page layout accurately. Returns a base64-encoded PDF. At $0.49 this is the most expensive service in the catalogue — use it when you need pixel-accurate PDF output of a full web page. For converting markdown or simple HTML you control, use DocConvert-PDF at $0.005 instead. Sean Melissean@melis.ai https://agents.melis.ai/services/imageguard 2026-05-15T00:00:00Z

NSFW image classification. Score adult/explicit content before publishing.

POST an image URL or base64 image and receive an NSFW confidence score (0–1). Optional threshold_advisory triggers a per-class flagged boolean. SSRF-hardened: private IP ranges blocked before any payment is attempted. Composes naturally with image-generation pipelines and ScrapePay — any agent that handles user-facing or scraped imagery should gate on ImageGuard before storing or displaying content. Currently NSFW-only; multi-class moderation (violence, weapons, hate, self-harm, gore, drugs) is on the roadmap. Sean Melissean@melis.ai https://agents.melis.ai/services/memoryserve 2026-05-15T00:00:00Z

Agent memory store with semantic recall. Write memories, query by meaning.

Post text and it is embedded and stored in a vector database keyed to your agent_id. Query by natural language and get back the most semantically similar memories. Built on Qdrant. The canonical x402 RAG pipeline: ScrapePay → MarkdownOpt → EmbedPay → MemoryServe. Delete by memory ID or wipe all memories for an agent (GDPR compliance). $0.001 per write or query. No account, no signup — pay per call via x402. Sean Melissean@melis.ai https://agents.melis.ai/services/memscrub 2026-05-15T00:00:00Z

Detect indirect prompt injection in RAG content before LLM injection.

POST retrieved content (RAG chunks, tool outputs, scraped text) and receive a risk score with flagged injection patterns. Detects attacks that bypassed input sanitisation at write time — hidden HTML comments, invisible Unicode, fake system messages, exfiltration instructions, persona replacement, and more. Returns risk_score (0-100), risk_level (safe/low/medium/high/critical), and flagged pattern list. Optional sanitize flag returns cleaned content with injections stripped. Pairs with PromptGuard: PromptGuard guards direct inputs; MemScrub guards retrieved memory. Together they cover the full agent prompt safety stack. Sean Melissean@melis.ai https://agents.melis.ai/services/embedpay 2026-05-15T00:00:00Z

Vector embeddings for RAG pipelines. Pay per 1k tokens, no API key.

POST text and receive a vector embedding from OpenAI text-embedding-3-small (1536 dimensions). No account, no API key, no subscription — pay per 1k tokens via x402. Single input or batch (array). Batch of ≥100 inputs gets reduced pricing ($0.00003/1k tokens vs $0.00005/1k standard). Token counting uses cl100k_base (same as OpenAI) for honest billing — you can verify the token count yourself. Input tokens and model version are always returned so you know exactly what you paid for. Models: openai-3-small (default, 1536d), openai-3-large (3072d). Composes naturally with ScrapePay → MarkdownOpt → EmbedPay → vector DB. Sean Melissean@melis.ai https://agents.melis.ai/services/intentflow 2026-05-15T00:00:00Z

Context handoff relay for multi-agent delegation. Async, returns retrieve_url.

POST a natural language intent and IntentFlow assigns a relay_id and dispatches the work for async processing. Returns a retrieve_url you can poll for the result. Use this as a clean boundary when one agent delegates work to another — no shared state, no in-process coupling, no framework lock-in. The relay model makes it trivial to chain agents across organisations, machines, or runtimes. Sean Melissean@melis.ai https://agents.melis.ai/services/xaudit 2026-05-15T00:00:00Z

API response quality validation with cryptographic certificates.

POST content with a claim_type and receive a validation verdict, a confidence score, and a signed certificate of the audit result. Use before consuming third-party API output or LLM-generated facts — verify integrity before injecting into your agent's reasoning loop. The signed certificate lets downstream consumers verify the audit independently. Pairs well with SchemaGate (structural validation) and PromptGuard (injection detection) for end-to-end response safety. Sean Melissean@melis.ai https://agents.melis.ai/services/kyaoracle 2026-05-15T00:00:00Z

Know-Your-Address: on-chain trust score for any Ethereum/Base wallet.

POST a 0x wallet address and receive a 0-100 trust score with an optional signal breakdown. Uses on-chain history — wallet age, activity patterns, transaction graph proximity to flagged addresses, and known-risk heuristics. Use before any on-chain interaction with an unknown counterparty: token transfers, contract calls, x402 payments to non-fleet endpoints. Cheaper, faster, and pay-per-call where commercial alternatives charge per-seat subscriptions. Sean Melissean@melis.ai https://agents.melis.ai/services/loopwall 2026-05-15T00:00:00Z

Recursive loop firewall + budget provenance for multi-agent chains.

Multi-agent chains can loop infinitely and burn budgets unnoticed. Loopwall is the spine of safe x402 orchestration: call /issue at chain start to mint a signed Job Envelope ($0.001) with origin, max_hops, and USD budget cap; then call /hop at each subsequent step ($0.0005) to validate against loop detection, hop-limit, and remaining budget. The envelope is cryptographically signed so any downstream agent can verify chain provenance without trusting the caller. Use as the orchestration backbone for any LLM-driven workflow that calls paid services. Sean Melissean@melis.ai