Video models
AI video generation models
Text-to-video. Image-to-video. Short-form for social, long-form for ads. Priced by the second.
All video models on Coinis
ByteDance · VIDEO
Seedance 2.5
Native 30-second single shots. Up to 4K. 50 multimodal references. Live on Coinis.
Google · VIDEO
Google Omni Flash
The talk-to-edit AI video model. Native synced audio. Edit clips by conversation.
XAI · VIDEO
Grok Imagine 1.5 Preview
Grok Imagine 1.5 Preview turns a product photo into a motion ad.
From $0.09 / second
View →MINIMAX · VIDEO
Hailuo 02 / 2.3
1080p cinematic video from text or image. Advanced physics modeling.
From $0.14 / second
View →KUAISHOU · VIDEO
Kling 2.5 (and 3.0)
Kling AI is Kuaishou's video generation model family
From $0.07 / second
View →BYTEDANCE · VIDEO
Seedance 2.0 & 1.5
Cinematic text-to-video from ByteDance, from $0.06/sec.
From $0.06 / second
View →OPENAI · VIDEO
Sora 2 / Sora 2 Pro
Sora 2 is OpenAI's text-to-video and image-to-video model
From $0.17 / second
View →GOOGLE · VIDEO
Veo 3 / Veo 3.1
Veo 3 is Google DeepMind's text-to-video and image-to-video model
From $0.05 / second
View →ALIBABA · VIDEO
Wan 2.5
Alibaba text-to-video with native audio mixing and bilingual prompts.
From $0.09 / second
View →Other categories
One wallet for every model.
Free tier. No credit card. Every model on one wallet. No accounts to juggle.
Start free