General Utilities x402 offerings

Extract text from an image by URL (OCR): PNG/JPG/WEBP/TIFF/BMP of a screenshot, scan, receipt, chart or photo -> the readable text, via the Tesseract engine. Keyless, no LLM. Use it to read text an agent can only see as an image. SSRF-guarded; max ~10MB.

Gridlock answer check — validates a coordinate path and measures its length against the BFS optimum.

Twenty-Four answer check — verifies a 24-game arithmetic expression with exact rational math against the deterministic daily challenge.

Chess Daily answer check — legally validates a complete UCI principal line against the pinned daily puzzle.

Extract concrete action items, priority and deadline signals from messy text

Turn a messy human request into an execution-ready goal, constraints, ambiguity signals and one question only if needed

Decide whether an agent should ask the human or safely infer and continue

Fortune cookie with unique fortune and lucky numbers for AI agents.

LLM chat completion processed in Germany. No training on inputs; usage logs exclude prompt/completion content. Responses are temporarily cached for redelivery.

LLM chat completion processed in Germany. No training on inputs; usage logs exclude prompt/completion content. Responses are temporarily cached for redelivery.

Takes a message history and a character budget and returns a shortened history together with a full account of what it cost. Four stages run in fixed order: pin protects messages that must survive (roles listed in keep_roles, the last keep_last_n messages, and anything you marked pin), dedupe removes later near-duplicates of an earlier message of the same role using word-overlap similarity, trim shortens unprotected survivors to max_message_chars at the last sentence boundary, and drop removes…

Inspect, check, split, merge, extract pages, rotate, linearize, optimize, strip metadata, encrypt, decrypt or repair PDFs from public HTTPS URLs. POST /v1/pdf with operation, input_urls and options. …

Text and embedding similarity scoring: cosine match and dedupe decisions at fixed model precision. POST /v1/semantic with {text_a, text_b} and get a similarity score as one JSON object. Deterministic…

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/sen…

Rule-based named-entity recognition for English text, from patterns and word lists rather than a trained model: persons, organisations, places, dates, money, percentages, emails, URLs and products, w…

Parse a URL query string into an object, or build one from an object. mode: parse (default) | build.

Compute the date of Easter Sunday for a given year using the Anonymous Gregorian algorithm (Meeus/Jones/Butcher). Also returns Good Friday, Ash Wednesday, Palm Sunday, Pentecost, and the day-of-year …

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

Levenshtein edit distance between two strings, plus a 0-1 similarity ratio.

Safely evaluate an arithmetic expression (+ - * / % ^ and parentheses). No code execution - a real parser, not eval.

Decompress a base64-encoded Brotli payload. Returns the result as utf8 (text) or base64 (binary). Refuses to expand past 10MB to defend against zip bombs.

Run a regular expression against text. Returns up to 100 matches with index and capture groups. Pattern ≤ 200 chars, text ≤ 10KB.

Compress a string with gzip (RFC 1952) and return it as base64. Reports input bytes, output bytes, and the compression ratio so you can decide if it was worth doing. Input can be plain text (utf8) or…

Heuristic user-agent string parser: browser, version, OS, device class, and bot detection.