LiveFlagship
Google DeepMind · video
Veo 3.1
Cinematic text-to-video with native audio, up to 4K.
Generate video Text to video
Model catalog
One prompt box, one credit balance, no model-by-model subscriptions. Veo 3.1 and Nano Banana render today; the rest of the lineup is rolling out — free members get first access.
Google DeepMind · video
Cinematic text-to-video with native audio, up to 4K.
Kuaishou · video
The photorealism benchmark — people, fabric, and physics that hold up.
Alibaba · video
Fast, expressive motion at a budget-friendly credit rate.
ByteDance · video
Native audio-video: synced lipsync, SFX, and music in one pass.
MiniMax · video
High-energy action shots with dramatic camera movement.
OpenAI · video
World simulation — and why Avyd routes those jobs elsewhere.
Google DeepMind · image
Instant Gemini image generation — frames, thumbnails, and stills.
Black Forest Labs · image
Pro-grade image generation with clean typography and editing.
How credits work
1 credit = 1 second of Standard video. Faster or higher-fidelity tiers use multipliers, images are 1 credit each, and new models join the same table when they launch — so switching models never means another subscription.