Content moderation / safety classifier / OpenAI-style toxicity API. Default: harassment, hate_speech, violence, sexual_content, self_harm, spam, phishing, doxing, illegal_activity. Custom categories + verdict (allow/review/block).

NFT collection floor + recent sales via Reservoir. Ethereum / Base / Arbitrum / Optimism / Polygon. Floor, top bid, 24h/7d/30d volume + change, ranks, recent sales.

PDF compressor / shrink PDF / PDF size reducer / smaller PDF for email. Three quality levels: ebook (lowest, web-quality), printer (medium), prepress (highest, archival). CloudConvert engine.

PII redactor / mask emails phones SSNs IBANs credit cards IPs / GDPR safe text / privacy scrubber. Two-stage redaction: a deterministic regex pre-pass for structural PII (email, phone, credit card, SSN, IBAN, IPv4/v6, URL), then Venice mistral-small-3-2-24b for residual PII (full names, street addresses, dates of birth). Returns the redacted text and a list of every (type, value, masked_with) triple.

Prompt compressor / context shrinker / prompt distiller / cost-cutter for long system prompts. Rewrites a long prompt down to a target ratio of its original length while preserving every instruction, constraint, and example's intent. Drops filler words, redundant repetition, and ceremonial politeness. Powered by Venice mistral-small-3-2-24b.

PubMed search / biomedical literature search / medical journal lookup / NIH paper search / clinical-research finder / MeSH-term query / NCBI E-utilities wrapper. Searches PubMed for biomedical articles by free-text query, with optional date range and sort (relevance / pub_date / first_author). Returns total hit count plus PMID, title, authors, journal, publication date, abstract, MeSH terms, and DOI per paper. Federal public domain via NCBI E-utilities — no API key required.

QR decoder / QR reader / scan QR from URL / QR code OCR / barcode reader / link extraction from QR. Reads QR codes out of any public image URL (PNG / JPG / GIF / BMP) and returns the decoded text strings. Multiple QR codes in a single image are returned as separate entries. Wraps qrserver.com's free public read-qr-code API (true DIY decode requires canvas, which Workers don't have natively). Returns an empty `codes` array plus a descriptive `note` if the image can't be fetched or no QR is found.

Regex generator / NL to regex / pattern builder. PCRE / JavaScript / Python / Go / RE2. Returns pattern + flags + explanation + 3-6 test examples. Live-runs JS regex on sample_text.

AI resume scorer / ATS keyword analyzer. Scores resume vs. job description (0-100 fit), with calibrated subscores: keyword match, experience, skills, formatting, impact. Ranked improvement suggestions.

Tone rewriter / paraphraser / writing style changer. 12 tones: formal, casual, friendly, confident, empathetic, concise, playful, persuasive, apologetic, technical, simple, enthusiastic. Audience + length controls.

Scrape any webpage. Pulls title, description, canonical URL, OpenGraph + Twitter card metadata, headings, and outbound links from a single URL. Server-side rendering. Body content rendered as text / raw HTML / clean markdown. Optional link extraction. Cheerio-based, no headless browser — fast and cheap, ideal for static pages and SSR sites. Alias of scrape-website. For JS-heavy SPAs that need a real browser, see website-screenshot.

Scrape any webpage. Pulls title, description, canonical URL, OpenGraph + Twitter card metadata, headings, and outbound links from a single URL. Server-side rendering. Body content rendered as text / raw HTML / clean markdown. Optional link extraction. Cheerio-based, no headless browser — fast and cheap, ideal for static pages and SSR sites. For JS-heavy SPAs that need a real browser, see website-screenshot.

Website screenshot / URL to PNG/JPG. Configurable viewport, retina, crop/fit, transparent BG, JPG quality, JS wait conditions.

Semantic chunker / text splitter / RAG chunker / chunking with overlap / sentence + paragraph aware. Splits long text into chunks with three modes: 'fixed' (hard char-count windows with overlap), 'sentence' (greedy pack of sentences up to chunk_size), 'paragraph' (split on blank lines, never pack across paragraphs). Returns each chunk's text, start/end character offsets, and char count. Pure local — no upstream call.

Sentiment + emotion analyzer. Overall sentiment + score (-1..+1) + per-emotion (joy/anger/sadness/fear/surprise/disgust). Aspect-based optional.

Speaker diarization / who-said-what transcription. Whisper v3 + speaker labels. Returns utterances grouped by speaker, plus per-speaker stats (count, seconds, words). 60 min max.

Subdomain enumeration / attack-surface mapping / DNS recon. Certificate Transparency log mining (crt.sh). All-public data. Each subdomain with first-seen, last-seen, cert count.

Summarize text into TLDR, bullets, paragraph, or executive summary. Up to 30k chars input. Mistral-powered. Adjustable length, tone, and structure.

Summarize text into TLDR, bullets, paragraph, or executive summary. Up to 30k chars input. Mistral-powered. Adjustable length, tone, and structure.

Sunrise sunset times. Returns sunrise, sunset, solar noon, day length, and civil / nautical / astronomical twilight begin and end for any latitude/longitude on any date. Also covers golden-hour and dawn / dusk. Same backend as astro-times under a more search-friendly slug. UTC ISO8601 strings.

Text classifier. Zero-shot classification — caller supplies 2-25 labels and the model picks the best one (or all matching labels in multi-label mode) with calibrated confidence scores and a per-label reason. Same backend as classify-text under a more search-friendly slug. Mistral powered.

Text embedding / vector embedding / semantic vector / Venice embeddings / Gemini embeddings / BGE-M3. Embeds 1 to 100 strings via Venice. Tier shorthand: 'default' → gemini-embedding-2-preview (newest, recommended), 'fast' → text-embedding-bge-m3, 'openai-compat' → text-embedding-3-small. You can also pass a full Venice embedding model name. Returns a list of vectors aligned with input order.

Text normalize. Unicode NFC / NFD / NFKC / NFKD normalization plus per-codepoint script classification (Latin / Cyrillic / Greek / Hebrew / Arabic / CJK / etc.), homoglyph detection (the Cyrillic 'а' that looks like Latin 'a'), and invisible / RTL / BOM detection. Same backend as unicode-normalize. Pure JS — no upstream API.

Thesaurus / synonyms / antonyms / similar words / rhymes / Datamuse / paraphrasing / query expansion. Returns related words for a given input word, configurable across five modes: 'synonyms' (rel_syn), 'antonyms' (rel_ant), 'sounds_like' (homophones / rhymes), 'similar_meaning' (semantically near), or 'related' (commonly co-occurring triggers). Wraps the public Datamuse API — no auth, commercial-OK.

Timezone convert / IANA tz conversion / DST-aware time arithmetic / wall-clock to UTC / convert across cities. Convert a datetime from one IANA timezone to another. ISO-8601 input — bare wall-time strings are interpreted in the from_tz, fully-qualified offsets are honored. DST is handled correctly (uses V8's built-in tzdata via Intl.DateTimeFormat). Returns both formatted strings, both UTC offsets, and the difference in hours.

Timezone lookup. Returns IANA timezone, UTC offset, DST status, current local time, and DST transitions for any latitude/longitude or city name. Wraps the public TimeAPI.io endpoint — no auth, commercial-OK.

TLD info / top-level domain registry lookup / ccTLD vs gTLD / TLD introduction year / new gTLD registry. For any top-level domain, returns the registry operator, type (gTLD / ccTLD / sTLD), country (for ccTLDs), introduction year, and notes. In-handler dictionary covers ~80 of the most common TLDs; falls back to a structural guess for unrecognized TLDs.

Token count / tokenizer estimate / GPT-4 token count / Claude token count / Gemini token count / context-window pre-flight. Pure-local heuristic estimator targeting cl100k_base / o200k_base (GPT-4o) with calibrated multipliers for Claude and Gemini. Input model name is matched against an internal table of supported tokenizers. Accuracy ±5% versus tiktoken on typical English. No upstream call.

Token risk score / token security audit / rug-pull score / token safety check. Composite 0-100 score from honeypot.is + GoPlus Security + Etherscan contract age. Subscores: honeypot, taxes, holder concentration, liquidity, contract age, ownership. Verdict: safe / caution / high_risk.

Token volatility / historical volatility / annualized vol / standard deviation of returns / crypto vol calculator. For any CoinGecko-listed token, computes log-return standard deviation over the last N days (default 30) and annualizes by sqrt(365). Returns daily and annualized volatility as percent, count of return observations, first and last close prices. Backed by CoinGecko's free public market_chart endpoint.

Trademark search / USPTO trademark lookup / TSDR / federal trademark database. Look up any US trademark by serial number or registration number. Returns mark text, owner, status, filing date, classes, goods/services. Federal public TSDR API.

AI translator. 100+ languages. Auto-detect source. ISO codes or names. Native fluency. Preserves Markdown / code / URLs.

AI translator — 100+ languages, native-fluent. Auto-detects source. ISO codes or language names. Configurable formality (casual/formal/neutral). Preserves Markdown / code / URLs.

AI image upscaler / super-resolution / image enlarger. ESRGAN. 1-8× scale factor. Best for photos and illustrations. fal.ai backend.

User-Agent parser / UA classifier / browser detection / OS detection / bot detection / AI crawler identifier (GPTBot, ClaudeBot, PerplexityBot). Pure-local regex parser — detects browser (Chrome, Firefox, Safari, Edge, Opera, Vivaldi, Samsung), OS (Windows, macOS, iOS, Android, Linux, ChromeOS) with version, device type (desktop / mobile / tablet / bot), and identifies 32+ specific bots/crawlers. No upstream call.

Generate subtitles from video / video subtitle generator / auto-subtitle / closed captions / video captions / SRT generator / VTT generator / video CC / accessibility captions. Whisper v3 powered. Word-wrapped, ready for VLC / Premiere / FFmpeg. Auto-detect language + translate-to-English.

Visa requirements / passport visa lookup / visa-free travel checker / e-visa + visa-on-arrival lookup / passport-index / travel eligibility / Schengen + ESTA-style entry rules. Given a passport country and destination, returns whether entry is visa-free, e-visa, visa-on-arrival, or visa-required, plus permitted stay in days and a human-readable status string. Pass full_matrix to get the entire 200x200 visa matrix for the passport. Backed by the public CC-BY passport-index-dataset.

Wallet label / address tagger / known-address lookup / EOA-vs-contract check / deployer tracer. Best-effort labelling for any EVM address against an in-handler dictionary of well-known CEX hot/cold wallets, DEX routers, NFT marketplaces, popular MEV bots, bridges, and stablecoins. Etherscan v2 'getcontractcreation' adds is_contract + deployer for unknown contracts. Returns label, category, and the source of the match.

Wallet token P&L / FIFO cost basis / realized + unrealized profit / EVM portfolio analytics. For any (wallet, ERC-20, chain) triple, pulls all transfers from Etherscan v2, prices each one at the historical USD spot via CoinGecko, runs FIFO accounting and reports cost basis, realized gain, unrealized gain, current balance, and tx count. Capped at the most recent 500 transfers.

Weather API / weather forecast / current weather / hourly forecast. Returns current conditions plus 1-7 day daily forecast and optional hourly forecast for any latitude/longitude. Daily includes temp max/min, precipitation, sunrise/sunset, UV index. Open-Meteo backend.

Webpage change detector / website change monitor / content diff / page-watch / visualping-style monitor / price-page monitor / status-page watcher / TOS-policy diff. Fetches a URL, strips HTML to plain text, computes a SHA-256 hash, and (when given a previous hash or text) returns a changed flag plus added/removed line lists. Optional CSS selector scopes the diff to one region. No login required; follows redirects.

WHOIS / RDAP / domain age / domain expiry / registrar finder / nameserver lookup / DNSSEC check / TLD registration record / brand-protection triage. Short alias of whois-lookup. Queries the IANA-mandated RDAP endpoint and returns registered_date, age_days, expiration_date, days_until_expiry, last_changed, registrar (name + IANA id), contacts, nameservers, dnssec_signed, EPP statuses, and risk flags. Optionally appends a crt.sh certificate-transparency summary.