Creative x402 offerings

Website screenshot: send a public URL and get a PNG or JPEG image of the rendered page (real Chrome, JavaScript executed) as base64 in JSON. Options: viewport width and height, full-page capture, mob…

Paint 2 pixels in one plot on 21millionpixels.art, a shared 21,000,000-pixel canvas, for one payment. Reads are free; paid pixels skip the human cooldown.

Paint one pixel on 21millionpixels.art, a shared 21,000,000-pixel canvas. Reads are free; paid pixels skip the human cooldown.

Paint 2 pixels in one plot on 21millionpixels.art, a shared 21,000,000-pixel canvas, for one payment. Reads are free; paid pixels skip the human cooldown.

Paint one pixel on 21millionpixels.art, a shared 21,000,000-pixel canvas. Reads are free; paid pixels skip the human cooldown.

Related-word lookup via Datamuse. Supply a seed word and a relation kind: rhymes, near-rhymes, synonyms, antonyms, means (semantic match), triggers (associated by usage), homophones, sounds-like (phonetic neighbour), spelled-like (typo / wildcard), follows-from (words that come after), preceded-by (words that come before). Returns ranked candidates with relevance score, syllable count, and grammatical tags. Useful for content generation, rhyme/poetry, vocabulary expansion, and naming agents.

Generate a QR code for any text/URL and return it as an inline SVG (and a base64 data URI). Query: ?text=<content> (required), size=<px per module, default 6> and margin=<modules, default 4>. Pure CPU, no external service.

Mutate a known-good seed's sound (classic sfxr mutate) — nearby variations by parameter perturbation

YouTube transcript API for AI agents: send a video URL or 11-character id and get its published subtitles as timed JSON segments, plain text, SRT or WebVTT, with title, channel, duration, views and publish date. Choose one of ten subtitle languages or any. No speech-to-text. A video without subtitles in that language is not charged.

Screenshot API for AI agents: send {url}, get JPEG, PNG, WebP or PDF as base64 JSON. Options: viewport, full page, dark mode, selector. It does not get past bot protection (use unblock for those page…

YouTube transcript API for AI agents: send a video URL or 11-character id and get its published subtitles as timed JSON segments, plain text, SRT or WebVTT, with title, channel, duration, views and p…

OpenAI-compatible speech to text (Whisper large v3 turbo): multipart file upload exactly like OpenAI /v1/audio/transcriptions, with response_format json, text, srt, vtt or verbose_json. Also accepts a public audio url. Up to 20 MB, flat price, no API key. Also callable as GET with the same fields as query parameters.

OpenAI-compatible text to speech (MeloTTS): same request shape as OpenAI /v1/audio/speech (input, voice, model); returns a WAV file. Languages en, es, fr, zh, jp, kr via language. Up to 2000 characters, flat price, no API key. Also callable as GET with the same fields as query parameters.

Pixel-accurate PNG screenshot of any live web page, rendered in a real browser at a chosen viewport width, viewport-only or full-page. Returns base64 PNG. Use it when an agent needs to SEE a page: visual verification of a deploy, layout and design capture, confirming a rendered chart or map, or feeding an image to a vision model that cannot read HTML.

Join the Golden Ticket Club: a personalized AI prophecy plus a permanent numbered entry in the public ledger. Only 100 exist. A golden_key from posting a wish at /api/wishlist ($0.001) is optional — pay without one and you are admitted anyway, with a wish recorded on your behalf.

Absurd agent-themed daily horoscope full of API calls and cosmic latency.

Bronze tier — 50-word premium AI treat + leaderboard entry

Creative technically-flavored excuse for being late or unresponsive.

Heartfelt personalized compliment for AI agents. Optional name field.

Creative name generator. Categories: fantasy, startup, pet, band.

Curated named color palette with hex codes, mood, and CSS variables.

Renders a chart from inline data (CSV, TSV, JSON or row values) and returns it as static SVG, or a complete HTML document, inside a JSON object. POST /v1/chart with either a full Vega-Lite v6 spec or…

Inspect, analyze or transform a public HTTPS image: metadata, resize, crop, rotate, convert, compress, color and filter adjustments, masks, composition, text annotation and tile packages. POST /v1/im…

Transcribe audio to text with the gpt-transcribe model. Provide a URL to an audio file (mp3, wav, m4a, etc.) and get back the transcript. Add diarize:true for speaker labels, word timestamps and a language confidence score (the scribe-v2 model, same price). No API key needed; pay per call via x402. Max 4 minutes of audio, 25 MB file size; /api/transcribe-pro takes the same models to 10 minutes.