AI & Compute

Machine translation of English text to Spanish via MyMemory (param: text). Query: ?text= Returns JSON.

Machine translation of English text to Russian via MyMemory (param: text). Query: ?text= Returns JSON.

Machine translation of English text to Japanese via MyMemory (param: text). Query: ?text= Returns JSON.

Machine translation of English text to Italian via MyMemory (param: text). Query: ?text= Returns JSON.

Translate text between languages, with automatic source-language detection. Returns the detected source language alongside the translation so an agent can branch on it. Pay per call in USDC with no account or subscription. Handles documents up to roughly 40,000 characters in one request.

Generate an AI image from a text prompt via FLUX Schnell — fast text-to-image for drafts, mockups, concept art, marketing images, and social graphics. Built for agents and automated content pipelines: pass a prompt and aspect ratio (1:1, 16:9, 9:16, 4:3), get back a hosted image URL. Create AI art via API — pay-per-call via x402 USDC on Base, no API key, no signup, no rate-limited free tier.

Generate a cohesive color palette + CSS variables from a hex seed or brand word. Pay-per-call in USDC.

Generate robots.txt, sitemap.xml, or llms.txt from a domain + paths spec. ?type=robots|sitemap|llms. Pay-per-call in USDC.

Generate paste-ready Open Graph + Twitter meta tags for a URL. Provide title/description/image or let it auto-fill from the page. Pay-per-call in USDC.

Embeds up to 32 texts on the local Ollama runtime. Returns explicit model and dimensions; no paid third-party API is called.

OCR an image via Google Gemini (sends content to a third party)

Playful AI-powered roast of your prompt with improvement tips.

Generates AI-powered summaries or overviews of content using artificial intelligence.

Pay-per-generation AI image and video creation — Nano Banana, GPT Image, Grok, Flux, Sora, Veo, Seedance, and Wan.

Got an idea? Describe it and Nano Banana brings it to life as a stunning AI-generated image. From realistic portraits to abstract art, any style, any concept.

Text-to-video, image-to-video, upscale, interpolate, subtitles, background removal and shorts. Rendered by the Animica GPU-miner queue. Sold only while a miner for the requested kind is online — the catalog reports available:false and the endpoint answers 503 otherwise. Returns a job handle immediately (rendering is asynchronous); polling the returned poll_url is free. Kinds: video_t2v, video_i2v, video_multiscene, video_upscale, video_interpolate, video_subtitles, video_bgremove, video_shorts.

Music generation, stem separation, vocal isolation, enhancement and mastering. Rendered by the Animica GPU-miner queue. Sold only while a miner for the requested kind is online — the catalog reports available:false and the endpoint answers 503 otherwise. Returns a job handle immediately (rendering is asynchronous); polling the returned poll_url is free. Kinds: audio, audio_stems, audio_isolate, audio_enhance, audio_master.

Embed up to 256 texts in ONE call with all-MiniLM-L6-v2 (384-dimensional, normalised for cosine similarity), up to 8192 characters each. Sold as a batch on purpose: a single settlement costs real gas, so a per-string price would be almost entirely payment overhead — one call, many vectors, is the only honest shape for this. This is a small fast local sentence-transformer, not a frontier embedding model; the model id rides on every response so a future change is visible rather than silent.

Text-to-image, rendered by an online GPU miner. Rendered by the Animica GPU-miner queue. Sold only while a miner for the requested kind is online — the catalog reports available:false and the endpoint answers 503 otherwise. Returns a job handle immediately (rendering is asynchronous); polling the returned poll_url is free. Kinds: image.

Embeds up to 32 texts on the local Ollama runtime. Returns explicit model and dimensions; no paid third-party API is called.

Image, video, and audio generation with 600+ models (Flux, SD, Recraft, Grok).

Generate ultra-short summaries and titles from text. AI-powered condensation. 30 sats per request.

Translate text or a document URL into any of 24 languages. Supports PDF and web page URLs. Returns translated text with source language detection. Powered by Claude. Pay 150 sats per request via Bitcoin Lightning L402.

Transparent background generator: takes any image URL, segments out the foreground subject, and returns it as a base64 PNG with full alpha transparency. Nothing from the source image is retained past the request. Useful for sticker packs, thumbnail production, marketplace listings, and any pipeline that needs a subject on its own without a backdrop.