Every agent-payable API.

Cross-asset intermarket synthesis for macro agents — bond yields, equities, commodities and FX read together to surface the dominant regime and the divergences that tend to lead price.

Agricultural commodity market outlook for grower and ag-trader agents. Synthesizes USDA WASDE and FAO data, futures price context, supply/demand balance, and exporter/importer outlooks for any crop.

Interest-rate differential and carry intelligence for FX agents — G10 policy rates, yield spreads and the carry-trade map that drives durable currency trends.

Seasonal intelligence brief for grower, ag-trader, and buyer agents. Returns global production outlook, weather situation, crop health, market summary, top risks, and action items in one read.

Deep-dive on any economic event for FX and macro agents — NFP, CPI, FOMC, GDP and central-bank decisions: what the print means, the base/bull/bear scenario tree, and the pairs in play.

Pest and disease risk assessment for grower and agronomist agents. Returns active threats, EPPO and FAO IPPC outbreak alerts, weather-conducive conditions, and IPM treatment guidance for any crop.

Crop yield forecast for grower and ag-trader agents. Synthesizes USDA WASDE and FAO supply/demand, production estimates, price implications, and a regional breakdown for any major crop.

Build a Vimshottari timing display with birth balance, nine mahadashas and nine antardashas of the active mahadasha at a reference instant. Uses actual nakshatra stay time and a 365.2425-day year; includes conventions and receipt. Public or synthetic inputs only. No event prediction or interpretation; bodies are not stored.

Build an astronomy or astrology tool with seven classical-body geocentric longitudes at one UTC instant, Tropical and versioned Lahiri Sidereal frames, conventions and a deterministic receipt. Public or synthetic inputs only. No interpretations, forecasts or predictive certification. Request and result bodies are not stored.

Build a reproducible chart view: Tropical and Lahiri Sidereal positions, Sidereal whole-sign houses, mean nodes, geometric aspects and panchanga for one UTC chart. Includes limitations and a deterministic receipt. Public or synthetic inputs only. No interpretation, forecast or predictive certification; bodies are not stored.

Choose a context budget before an agent run. Compare five extractive compilation budgets with token estimates and source coverage. Price basis: five compiler runs, the comparison table and the receipt digest. Uses caller-supplied documents; no answer generation, factual verification or guaranteed token-billing savings.

Compile 1-8 documents into a token-budgeted context pack, then measure exact retention of 1-32 caller-labelled evidence spans. Returns the pack, source-linked passages, input and output hashes, original and compiled token estimates, tokensSaved, source coverage, and requiredEvidenceRetentionPercent. Retention is exact span matching only: not accuracy, answer quality, verification, or hallucination prevention. Extractive and budget-bound. Request content is not stored.

Compress long documents and RAG inputs into token-budgeted, deduplicated context packs with source-linked provenance. Returns original and compiled token counts, so the saving is verifiable. Net-positive above N = fee / (r x p) tokens: r your reduction, p your input price. Extractive and budget-bound, so check includedPassages before relying on it. Ranks Latin, Cyrillic, Greek, Arabic and CJK; CJK coarser (bigrams). Not for tabular or heavily-structured payloads.

Evaluate exact retention of 1-32 caller-labelled evidence spans at exactly five ascending token budgets. Returns five source-linked Context Packs, per-run retention metrics, an evidence frontier, stable hashes, and a deterministic receipt digest. Price basis: five $0.01 evaluations. Retention is not truth, accuracy, answer quality, legal compliance, or hallucination prevention. Bodies are not stored.

Review a passage for Maha Principle epistemic classifications with a model-backed audit, not factual certification, legal advice, or human verification. Save the job reference and retrieve the completed result; job acceptance is not delivery. Short input excerpts may be retained in the result.

Maidenhair Fern (Delicacy) — Meditation on fragility and precision for handling delicate systems.

Maiko Twilight — Apprentice encounter for understanding long-term skill development and cultural mastery.

Mail Security Tools API: Graded email security score (0-100, A-F) for a domain. Scores SPF (30), DMARC (40), DKIM (25) and MX (5) from live DNS, with findings and the top 3 fixes. Bad input 400, unknown domain 404, never charged.

Mail Security Tools API: Prepaid email setup watch: up to 25 domains for 30 days, webhook on change. Pay once, then each domain's SPF, DMARC, DKIM (common selectors), MX and score are re-checked about once a day for 30 days. When something changes or breaks you get an HMAC-signed JSON POST at your https webhook_url (event watch.changed, kind changed|broke, before/after). A watch.created POST is sent right away. Webhook only, no email. Free status at GET /v1/watch/{watch_id}. Bad input 400, never

Mail Security Tools API: Bulk email security score: up to 100 domains in one call. Scores up to 100 domains (comma/space separated) for SPF, DMARC, DKIM and MX from live DNS: per-domain score, grade and issues plus a summary (grade counts, missing DMARC/SPF, worst 10). Built for MSPs and agents checking a whole client or vendor list. Bad input 400 and widespread DNS failure 502, never charged.

Check the status and tracking of a physical letter previously sent via POST /api/letters. Returns render status, expected delivery date, and (for certified mail) the USPS tracking number.

Check the status and tracking of a physical letter previously sent via POST /api/letters. Returns render status, expected delivery date, and (for certified mail) the USPS tracking number.

Main semantics audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Main semantics decision fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Main semantics repair plan fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Maine Coon — Bear — Anchoring companion for solid presence and grounding weight.

Measures the share held by the largest maintainer from supplied ownership weights. Missing facts are returned as null and named in unavailable_fields where applicable. Derived values disclose their method; source-backed values disclose source, time window and age.

Animate a photo of a person, or a paid generation, into a short looping GIF from a motion prompt, no account needed

Restyle a photo of a person from a text prompt: same face, any style. One 1024px PNG, no account needed

Maker (MKR) price in USD now, with 24h and 7d change — Genesis402 / UnyKorn Operator Network

Deepstate, the on-chain order-book exchange on Robinhood Chain. Per-maker time-at-top, notional rested, fills, and maker rewards earned for a market (token varies by market; see /deepstate/v1/markets).

Public-chain evidence that compares a transaction hash against a caller-declared payment mandate.

Full event history and statistics of one live bot

Follow subscription: a token for the live event stream for 24 hours

Live positions and the last 24 hours of events of one live bot

Mantle (MNT) price in USD now, with 24h and 7d change — Genesis402 / UnyKorn Operator Network

Mantle DeFi overview: TVL trend, top protocols, stablecoins, DEX volume, fees — Genesis402 / UnyKorn Operator Network

Source keyword register for supplier discussion passages with verified-note crosswalk; literal vocabulary only. Reuses exactly one existing qualified meeting-notes request. Supplied source goes to the existing Groq model in the USA; existing processor disclosure and cost/margin retained. Notes quotes/owners/deadlines are verified by the unchanged motor first. Extra rules are deterministic; no semantic deadline resolution or specialist advice.

Chat completion from an open AI model (Llama 3.3 70B by default; Llama 3.1 8B for speed), no account or API key: send messages (or a prompt), get the model's reply. Up to 24,000 characters in and 1,024 tokens out per call.

Rewrite a text in a requested style (clearer, shorter, formal, friendly, plain English…) keeping its meaning.

Summarise text into a short, faithful summary (optionally in a target language and word limit).

Named entities in a text: people, organisations, places, dates, money amounts, products and other notable items, each with its type and how many times it appears.

Classify a text into topic categories: from your own list of labels, or open topics if none given, with confidence.

Extract the key words and phrases from a text, most important first, with a one-line topic.

Text to speech: turn up to 2,000 characters into natural-sounding speech (MeloTTS), returned as base64 MP3. Languages: English, Spanish, French, Chinese, Japanese, Korean.

Line-by-line difference between two texts (up to 3,000 lines each): added, removed and unchanged lines in order, with counts.

Detect the language of a text: ISO code, language name, script, and confidence.

Read back values the paying wallet saved with /paid/memory/set: one key, or list your keys by prefix (keys, sizes and expiry, newest first). Another wallet can never see them.

Translate text into any language, with the source language detected and tone and formatting kept.

Sentiment of a text: positive, negative, neutral or mixed, a score from -1 to 1, the emotions present and a one-line reason.