Every agent-payable API.

Sui mainnet in one call: epoch, latest checkpoint, reference gas price, SUI price, total stake and every active validator with staking APY, commission and stake, sorted by APY.

Sui mainnet transaction by digest in plain JSON: status, time, checkpoint, sender, Move calls, gas fee in SUI, balance changes per address with coin symbols, created and changed objects, events.

Everything about a Sui mainnet address or SuiNS name (alice.sui): SUI balance and every other coin with symbol, staked SUI per validator with estimated rewards, USD value, its SuiNS name and latest outgoing transactions.

Watch a Sui address or SuiNS name in a loop and get only new transactions since your last call, with direction, SUI change, status and link, plus the balance. Pass the returned cursor on the next call.

Extractive summary (3 sentences) + top-5 keywords from any text.

Generate a summary of a given text using the GLM chat model.

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

Fetch a public web page and return a concise summary: title, 3-7 key points, a one-paragraph TL;DR and the page's main entities. Good for research agents that need the gist of a URL cheaply.

LLM-quality summary of long text as a paragraph, bullets or a one-liner. Reads for meaning (nuance, tone) — unlike the free extractive summarizer.

Summarize text (article, transcript, report) into a given number of sentences, via Claude Haiku 4.5. Preserves the source text's language. JSON body: {text: string (max 8000 chars), max_sentences?: integer 1-10 (default 3)}.

Summarize any text. Body: {"text":"long text here"}. Returns 3-5 sentence summary.

Summarize any text or URL. Styles: concise (default), bullets, eli5. MiniMax M2.7 (456B-parameter Mixture-of-Experts) inference.

Summarize any web page. Give a URL; Bob reads the page with Firecrawl and returns an 80-word summary with key points. Typical response 3 to 6 seconds. If the page cannot be read in time you get an error and are not charged.

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.

Summarize text. Classify sentiment. Rewrite. Extract keywords. Translate. Verb-path alias of POST /v1/cheap-errand ($0.01 USDC). Same handler + payment terms; path defaults task when body.task omitted (/v1/summarize→summarize, /v1/keywords→extract_keywords). Base via x402. No API key.

Summarize text. Classify sentiment. Rewrite. Extract keywords. Translate. Verb-path alias of POST /v1/cheap-errand ($0.01 USDC). Same handler + payment terms; path defaults task when body.task omitted (/v1/summarize→summarize, /v1/keywords→extract_keywords). Base via x402. No API key.

Summarize text. Classify sentiment. Rewrite. Extract keywords. Translate. Verb-path alias of POST /v1/cheap-errand ($0.01 USDC). Same handler + payment terms; path defaults task when body.task omitted (/v1/summarize→summarize, /v1/keywords→extract_keywords). Base via x402. No API key.

Summarize text. Classify sentiment. Rewrite. Extract keywords. Translate. Verb-path alias of POST /v1/cheap-errand ($0.01 USDC). Same handler + payment terms; path defaults task when body.task omitted (/v1/summarize→summarize, /v1/keywords→extract_keywords). Base via x402. No API key.

Fetch a PDF from a URL, extract its text, and return a concise AI-generated summary - factual, no information added beyond what's in the document. Body: {"url":"https://…/file.pdf","maxWords":200?}. Uses the same OpenAI-compatible gateway as /v1/chat/completions internally; the model that actually served is disclosed in the response.

Fetch a web page and return a concise summary and key points (SSRF-safe fetch + Claude).

Summarize a long text

Summarize a text with AI.

Give a URL, get a short summary of the page plus three to six key points, ready to drop into an agent's context. Fetches the page, strips navigation and boilerplate, and summarizes the main text with an LLM. HTML pages only; for a PDF use pdf_text, then ai_summarize_text. Use for research, news triage, link previews and deciding whether a page is worth reading in full. For the full text use extract.

Summarize any text using AI. Returns a concise summary.

Summarize text. Summarize up to 12,000 characters of text you send into a few sentences plus bullet key points. Use for long emails, documents, transcripts and tool outputs (for a web page by URL, use /summarize).

Summary or analysis of any text with local AI (Qwen3), in the same language as the text; follows your instruction if you add one (e.g. 'list the key points'). Up to 12,000 characters. Text is processed in memory and not stored.

The Standard Reserve (TSR), an on-chain reserve protocol on Robinhood Chain. Summary across reserve branches. Fields ending in _raw are 18-decimal integers as strings. Divide by 1e18 to get token amounts.

A short brief, about one page, on a topic you specify, researched on the live web at the time of the request, with every source linked. Typically 60-120 s; allow 180 s. POST {"topic":"..."}.

Use when you need a quick market snapshot for a South Korean district-month instead of raw trades. Input: region (5-digit LAWD_CD, e.g. 11680), month (YYYYMM). Output: JSON stats from MOLIT data excluding cancelled deals: count, median/avg price and price per m2 and per pyeong in KRW and USD, breakdown by area class, top complexes. Example: ?region=11680&month=202409

Wikipedia article summary (extract, short description, thumbnail image, canonical link) for a given title — CC BY-SA content, attribution included in every response. Parameters: ?title=<exact article title> (e.g. Bitcoin), ?lang=<language code> (default en).

The plain-language summary of a Wikipedia article in any language edition: title, short description, lead extract, canonical URL, thumbnail and coordinates when the subject has them. Falls back to the best matching title. Query: ?title=Guadeloupe&lang=fr

3-5 sentence extractive summary of the latest news matching q (limit 1-50, default 10): lead sentence + de-duplicated headlines, high-importance first

Sunrise, sunset, solar noon, civil dawn/dusk, morning and evening golden hour and day length for any coordinates and date, in the place's local time zone; polar day/night flagged. Offline astronomy. For travel, tourism, photography, events and outdoor-planning agents.

Sunrise, sunset, solar noon, civil dawn/dusk, morning and evening golden hour and day length for any coordinates and date, in the place's local time zone; polar day/night flagged. Offline astronomy. For travel, tourism, photography, events and outdoor-planning agents.

Compute sunrise, sunset, solar noon and day length for a latitude/longitude (east-positive) and date, using the NOAA sunrise equation. All times are UTC ISO-8601. Locations in polar day or night return null rise/set with a `polar` flag — a successful result, not an error.

Sunrise, sunset, solar noon, day length, sun elevation, moonrise, moonset, moon phase and illumination for any place (name or coordinates) and date. Use for photography, prayer and event planning, solar or outdoor work.

Sunrise, sunset, solar noon, civil dawn and dusk (UTC) and day length for any place and date, computed with the standard solar equations; handles polar day and night. No outside service. Use for photography, events and outdoor planning.

Sunrise/sunset via api.sunrise-sunset.org (keyless). Lat/lon[/date] → sunrise, sunset, solar_noon, day_length (UTC ISO).

Sunrise/sunset times

Supplied stockout cost - Before and after comparison: Before and after comparison for Supplied stockout cost. Supplied retail figures only. Local calculation and scenario analysis; no live inventory, account access, platform fee lookup or order execution. One of 25 profiles or calculations across 20 shared operations in this sector. 0.01 USDC includes one bounded before and after comparison deliverable.

Supplied tiered-weight shipping charge - Two-input scenario grid: Two-input scenario grid for Supplied tiered-weight shipping charge. Supplied retail figures only, up to 200 records. No platform access, live rates or order execution. One of 25 new profiles across 20 shared operations in this industry. 0.01 USDC includes one bounded two-input scenario grid report.

Supplied tiered-weight shipping charge - Single calculation: Single calculation for Supplied tiered-weight shipping charge. Supplied retail figures only, up to 200 records. No platform access, live rates or order execution. One of 25 new profiles across 20 shared operations in this industry. 0.01 USDC includes one bounded single calculation report.

Supplied tiered-weight shipping charge - Target gap calculation: Target gap calculation for Supplied tiered-weight shipping charge. Supplied retail figures only, up to 200 records. No platform access, live rates or order execution. One of 25 new profiles across 20 shared operations in this industry. 0.01 USDC includes one bounded target gap calculation report.

On-time in-full % and chargeback exposure.

Registers an RSA public key (2048-bit or larger, PEM) used to sign payment-decision requests. Keys are immutable per tenant; rotate by registering a new key_id.

Supplier and vendor risk score for any company domain. Returns a 0-100 stability score, risk tier, and named risk flags, with subsignals: domain age/expiry (WHOIS), TLS certificate status, DNS health (A/MX/SPF/DMARC), and 30-day news sentiment. Use for supplier due diligence and third-party domain screening before purchasing from, integrating with, or paying an unfamiliar vendor or counterparty. Call GET /supplier-risk?domain=acme.com. JSON response, no API key, $0.15 USDC per request via x402.

Returns supplier relationship status, risk indicators, and authorization evidence flags for LCG orchestration. Mock suppliers are explicitly labeled.

U.S. oil supply from the EIA weekly report: crude production, refinery utilization, crude imports and exports (thousand barrels per day), weekly change, 4-week average, change vs. a year ago, and net imports. Data, not trading advice.

Supply-chain health from deps.dev: OpenSSF Scorecard (14 checks — branch protection, signed releases, pinned deps…) plus stars, license and open issues

Converts each supplied storage segment into equivalent ageing at a reference temperature using a caller-supplied Q10 factor, then compares the sum with nominal shelf life. This empirical approximation is not a microbial model, food-safety decision, sensor feed, cold-chain certification or release authorization.