Models
Each model has a page with exact parameters, pricing, cURL/JS/Python examples and its own llms.txt to paste into your AI assistant.
Centaurus 1.0#
Centaurus 1.0 — cinematic video from text or an image.
Cinematic text-to-video with crisp detail, stable motion and strong instruction-following. 720p/1080p, multiple aspect ratios, 2–15s clips. $0.20/s @ 720p · $0.30/s @ 1080p (× duration).
Animate a reference image into a cinematic clip. Aspect ratio matches the source. 720p/1080p, 3–15s. $0.28/s @ 720p · $0.56/s @ 1080p (× duration).
Hera 1.0#
Hera 1.0 — image generation & editing, plus multi-shot video.
Cinematic image-to-video with multi-shot narrative support. 720p/1080p, 5/10/15s clips. $0.20/s @ 720p · $0.30/s @ 1080p (× duration).
Prompt-driven image editing. Upload 1–3 reference images and describe the change. $0.070 / run.
Multi-modal text-to-image. 1k/2k resolutions, 9 aspect ratios, generate up to 9 images per call. $0.056 / image (× num_images).
Zeus 1.0#
Zeus 1.0 — high-quality image-to-video, scalable and affordable.
Turn an image into a high-quality video with smooth motion. 480p/720p, 5s or 8s clips. $0.30 (480p, 5s) · $0.48 (480p, 8s) · $0.60 (720p, 5s) · $0.96 (720p, 8s) / run.
Budget image-to-video at 480p, 5s clips. Supports a negative prompt and automatic prompt expansion. $0.40 (480p, 5s) / run.