Block height, difficulty, peers, chain health — flat $0.001 per call, USDC on Base, no signup.

Pharmacokinetic simulation for one compound: walks the published model at one dose and cadence and returns the modelled serum curve over the requested horizon plus a 60-day washout tail. Deterministic math over published reference data -- not medical advice, not a prescription, and for relay to a human decision-maker rather than autonomous administration.

Text Moderation safety: Safety classification of a message or conversation with Llama Guard 3: safe/unsafe plus the 14 hazard categories (violent crimes, hate, self-harm, sexual content, ...).

Image generate: Generate an image from a text prompt with FLUX.1 schnell; returns PNG bytes (default) or base64 JSON.

Text Moderation rerank: Semantic reranking: score up to 100 documents against a query and return them best-first (RAG, search, dedupe).

AI Text Tools summarize: Summarize text as a paragraph, bullet points or a TL;DR, in any language, with a sentence limit.

Text Moderation pii: Detect personal data (email, phone, SSN, credit card with Luhn check, IP, IBAN, crypto address, name, address, date of birth, passport) with character offsets; optional redaction to [TYPE].

Text Moderation sentiment: Sentiment of one text or a batch of up to 50: positive/negative label, score and a signed polarity from -1 to 1.

Node network state: version, subversion, connections — flat $0.001 per call, USDC on Base, no signup.

Reviewer quality lookup. Returns quality score and review history for a wallet address that has left ERC-8004 feedback.

Full text of one section of the FDA Investigations Operations Manual (IOM). Get the id from GET /search?q=<keywords> or GET /chapter/:id. Use this when you need the complete, verbatim text of a specific IOM section for inspection-readiness or regulatory research, not a summary.

QR Code Generator batch: Encode up to 25 texts as QR Codes in one call; returns JSON with an SVG or matrix per item.

An agent preserving a supplied HTML inquiry handoff needs the partition of enabled submitters by effective method, resolved action and encoding before changing buttons or form ownership. No service/payload or conversion intent is inferred.

AI Chat (LLM) chat: OpenAI-compatible chat completion on Llama 3.3 70B or Qwen 2.5 Coder 32B (up to 32000 characters in, 1024 tokens out, optional JSON mode).

Speech speak: Convert text (up to 2,000 characters) into natural MP3 speech, returned as audio/mpeg bytes or base64 JSON (Deepgram Aura-1).

Summarize text. Classify sentiment. Rewrite. Extract keywords. Translate. When to use: cheap agent glue / probe steps for buyer-supplied text. Returns JSON for $0.01 per call in USDC on Base via x402. No API key. Local-fast NLP; no login scrape. Success JSON includes next_tasks hints for same-session follow-ups.

Vetted stablecoin yields: top stablecoin pools (DefiLlama, TVL>$5M, APY 1-25%) joined with each protocol's age and hack history, safest-yield first; optional ?chain= & ?limit=. No required params. Use when an agent needs where to park stablecoins with due-diligence already applied.

Simulate the selected Referrer-Policy response-header token across fixed synthetic HTTPS same-origin, cross-origin and downgrade targets; return only no-referrer, origin and URL-eligibility counts.

Text translation (Llama 3.2 3B): ?text=<up to 800 chars>&to=<target language, e.g. es, fr, de, ja> returns the translated text only. Use when an agent needs quick pay-per-call translation with no API key.

Text summarization (Llama 3.2 3B): ?text=<up to 1500 chars> returns a 1-3 sentence summary. Use when an agent needs to compress a passage cheaply before reasoning over it.