Documents & files

Deterministic data-format conversion — the shape work an LLM cannot do reliably token-by-token. POST {data, from, to}: JSON, NDJSON, CSV, TSV, or a SQL INSERT dump in; any of the same out. Handles RFC 4180 quoting (commas, quotes, newlines in values), flattens nested objects to dot-notation columns, unions ragged records into a stable column set, and parses SQL string literals with '' and \' escapes. No AI, no network — same input, same bytes, every time.

Convert a time between any two IANA time zones, with daylight saving applied from the runtime's own tz database. Returns both sides with their UTC offset, abbreviation and DST flag, plus the UTC instant and the difference in hours. Warns when the time you asked for does not exist or happens twice because the clocks change that day: the two cases that quietly make a hand-made conversion wrong.

Converts between wei, gwei, ether and any token decimals using exact integer maths - no floating point, no silent rounding. The mistake that costs real money is being off by a thousand on decimals.

Fetch a file from a public URL into your persistent Vaaya file library (server-side — no local download needed). Returns file_id and get_url. Max 100MB per file.

Convert any physical measurement — length, mass, volume, temperature, area, speed, pressure, energy, time, data storage & transfer rate, power, frequency, force, fuel economy (mpg/L per 100 km), angle. Auto-detects the category, handles US/imperial ambiguity, reports assumptions. Accepts natural-language queries ("what is 5 km in miles") and volume↔mass via density/substance. Deterministic and instant.

Normalize any messy money string into a typed decimal amount plus ISO 4217 currency — handles symbols, locale separators ($1,234.56 vs €1.234,56), magnitude suffixes (1.2M), accounting notation, and natural-language amounts — so agents can clean money values before converting or storing them, with no external data and a deterministic fast path.

Fetch any URL and get the raw body back — JSON parsed, everything else as text — from safe server-side egress. For data APIs (ArcGIS, government/open-data portals, blob storage) that /web/extract's markdown conversion mangles. No API key, SSRF-guarded, billed only on a usable 2xx response. Pass url as ?url= (GET) or a JSON body (POST).

Lexicon-based sentiment scoring: label a text positive, negative or neutral with a score and the positive and negative word hits behind it (AFINN-derived word list, not a trained model). POST /v1/sentiment with {text}. Deterministic. Pay per request in USDC; no account, no API key.

Document parser: turn a document into clean, agent-ready Markdown with metadata: DOCX, ODT, EPUB, RTF, HTML, RST, LaTeX and more. Returns title, author, date, language, word count, heading outline, table and image counts and the Markdown (headings and tables preserved). For PDF use pdf-extract; PPTX and XLSX are not supported. Params: file_base64 or url or content (one required), from (optional), max_chars (1000 to 200000, default 50000).

Convert documents between formats with pandoc: Markdown, HTML, DOCX, ODT, EPUB, RST, LaTeX, RTF, plain text and PDF. Input as text (content), file (file_base64, max 10 MB: docx, odt, epub, rtf) or url. Input format is detected automatically or set with from. Text outputs come back as content, binary outputs (docx, odt, epub, pdf) as file_base64. Local file includes and remote images are not loaded. Params: to (required), content or file_base64 or url, from, title.

Resize, crop-fit and convert images (PNG, JPEG, WebP, AVIF, GIF, TIFF, SVG input) to webp, png, jpeg or avif. Auto-rotates by EXIF. Use to shrink screenshots before sending them to a vision model, create thumbnails, or convert formats. Params: image_base64 or image_url (one required), width, height (max 4096), fit (inside default | cover | contain | fill), format (webp default), quality (1-100, default 80).

Domain registration lookup via RDAP (modern WHOIS). Returns registrar, registrar_url, created_at, updated_at, expires_at, days_until_expiry, name_servers array, status array, and registrant_country. Clean JSON, no raw WHOIS text to parse. Covers all major TLDs.

Render a URL or raw HTML string to PDF. Returns pdf_base64 (base64 PDF; decode to get raw bytes) and page_count. Provide url OR html, never both. Supports format (A4/Letter/Legal), landscape boolean, and margin settings (top/bottom/left/right in CSS units). Use for invoices, reports, or printable document generation.

Capture any URL as a PNG screenshot. Returns image_base64 (base64 PNG; decode to get raw bytes). Full JS rendering via Playwright, works on SPAs and dynamic content. Params: url (required), width px (default 1280), height px (default 800), full_page boolean, wait_ms.

Convert a JSON payload to TOON (Tokenized Object Notation), a compact pipe-delimited format that achieves ~60-70% token reduction versus equivalent JSON on time-series payloads. Accepts a raw array or an envelope {meta, data, result_type}. Max body: 512 KB (HTTP 413 if exceeded; checked before payment). Pay $0.005 per call via x402 USDC on Base, or use a bearer token from /token/purchase.

One SEC EDGAR filing by accession number: form, filing and acceptance dates, report period, 8-K items with descriptions, file number, XBRL flags, primary document and SEC URLs. Accessions submitted by filing agents also need ticker or cik. Covers each cached company's latest 1000 filings; a miss is 404 and not charged.

Wandelt CSV in JSON oder JSON in CSV um, ohne KI (Convert CSV to JSON or JSON to CSV, deterministic).

PDF to text: send an https link or base64 (up to 15 MB) and get the text page by page plus title, author, page count and dates. Text PDFs only: a scanned PDF without a text layer answers 422 and is not charged.

Humanize AI Text: Rewrites AI-sounding prose so it reads like a person wrote it — in any language, without dropping facts. Use when asked to humanize a text, make it sound less AI-generated or less like ChatGPT, or clean machine phrasing out of an article, post, email, product description or page. One-time purchase of the SKILL.md file (Agent Skills format), $0.05 USDC, yours forever incl. free re-downloads and new versions. Tested with a strong and a weak model; the card tells you where the we…

Recursive diff between two JSON documents: added, removed and changed paths.

Convert decimal degrees to degrees/minutes/seconds, or DMS back to decimal degrees.

Convert an integer to its English ordinal form (1st, 2nd, 3rd, 4th, 11th, 21st...).

Convert a number's string representation from one base (2-36) to another.

Convert an integer (1-3999) to a Roman numeral, or a Roman numeral back to an integer.

Rank up to 50 documents by relevance to a query in a single call - each document returned with its relevance probability, sorted highest first. Powered by Jev (TypeSafe System One). $0.001 per call, no OpenRouter or TypeSafe account needed. Try GET /rank/sample.

Convert text between case styles: snake_case, camelCase, PascalCase, kebab-case, Title Case, CONSTANT_CASE.

Convert an ISO 8601 datetime from one IANA timezone to another (handles DST automatically).

Parse a date/time string (ISO 8601 by default, or a given strptime format) into its components.

Convert a value between units of length, mass, volume or temperature (C/F/K).

Text in an image `url` via Google Lens: paragraph, sentence and word-level detections with bounding boxes. Optional `language`. Cheap OCR for screenshots, receipts, signs, slides.