General Utilities x402 offerings

$0.0002/MB. Zip any set of files into one downloadable archive — pass URLs or payloads, get a link back. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny

$0.001/page. Fill or flatten PDF forms programmatically — field values in, finished PDF out. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny

$0.0002/call. Decode a QR code from an image — the embedded text or URL back as JSON. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny

Labels up to 20 texts with 2 to 20 labels you choose, with a confidence from 0 to 1 and a one-line reason per text. One label per text, or several with multi true. Uses the chat model with JSON outpu…

Up to 15 question and answer pairs written from a text (max 30,000 characters). Each answer carries a supporting quote that is checked against the text; pairs whose quote does not occur in the text a…

Multilingual text embeddings (BGE-M3, 1024 dimensions) for up to 100 texts per call. For search, RAG and clustering.

Readability of a text in pure code: Flesch Reading Ease, Flesch-Kincaid grade, Gunning Fog, SMOG, Coleman-Liau and ARI, with counts of characters, words, sentences, syllables and complex words, and r…

Differences between two texts: mode lines, words or chars; the added, removed and unchanged parts with counts, a similarity ratio (2 x unchanged / both texts' units), and a unified diff for lines. Bo…

Rewrite a text in a chosen tone (neutral, formal, casual, simple, persuasive) and length (shorter, same, longer), keeping its meaning and language. Up to 3 variants. Workers AI (Llama 3.3 70B) writes…

Tone analysis of a text (max 10,000 characters): formality 0-1, sentiment, emotion scores, tone labels such as friendly, aggressive or urgent, and short suggestions. The reading level (Flesch-Kincaid…

Grammar, spelling and style check with LanguageTool: each issue with its message, the offending text, its position, up to five suggestions, the rule id and category, plus the corrected text with the …

Translation with Llama 3.1 8B: up to 6,000 characters per call, formatting, names, numbers and URLs kept, source language detected when not given. Language codes like en, tr, de, fr, es, ar, zh, or l…

Encode or decode text as base64, base64url, hex, URL (percent) encoding, HTML entities, punycode (domain names) or quoted-printable. Body { input, scheme, direction }, up to 1 MB. Invalid input to de…

LLM chat completion with Llama 3.3 70B (fast): send messages or a prompt, up to 2048 output tokens.

Answers a question from the given text only (max 30,000 characters), with supporting quotes and their character offsets. Each quote is checked against the text and dropped if it does not occur in it.…

Keywords and keyphrases from a text by RAKE (Rose et al., 2010) in pure code: phrases between stopwords and punctuation, scored by word degree and frequency, with counts. Stopword lists for en, de, f…

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 n…

Markdown to HTML with GitHub-flavoured tables and strikethrough, heading ids, the list of headings and links, and a word count. Raw HTML in the input is escaped unless allowHtml is true; links and im…

Uniformly select one original index and item from the input array. Equal values at different positions have separate chances. Uses the server OS CSPRNG. Returns consumed bytes for reproducible calcul…

Select one original index and item with probability weight divided by total weight. Weights must match items and be integers from 0 to 1000000000; at least one must be positive. Uses the server OS CS…

Uniformly permute all input items. Returns each original index and its item exactly once; equal values remain distinct positions. Uses the server OS CSPRNG. Returns consumed bytes for reproducible ca…

Identify the type and country of a company registration number. Detects Swedish org numbers, Finnish business IDs, German HRB numbers, LEIs, DUNS, and 20+ other formats. Pure algorithmic.

Estimate token count and cost for text across LLM models (GPT-4o, Claude, Gemini, Mistral, Llama). Algorithmic — no API calls.

Check if a specific date is a business day in a given country. Accounts for weekends and public holidays. Also returns the next business day if the given date is not one.