content-generation

Render a social image as PNG with exact typography, with the format given as a `size` argument rather than in the path. The text in the output is exactly the text supplied — no garbled lettering, unlike diffusion models. Responds with raw PNG bytes, not JSON.

Extract still frames from any video as JPEG, WebP or PNG - built for feeding video to a vision model. Choose the sampling: every frame, every Nth, a fixed rate in seconds, keyframes only, N evenly spaced, or exact timestamps; optionally windowed and size-capped. Up to 1000 frames per job. The result is a manifest listing every frame with its timestamp and its own download URL, available for 24 hours. Fixed price per job in USDC over x402; no account or API key. Input up to 100 MB.

Usage-based text generation, billed by output length (max $0.05/request)

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.