Run AI models on your own hardware with automatic optimization and a single endpoint
An API platform for video generation with image and LLM APIs planned
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Open source
Paid
Pricing
Not given
Wan 3.0: $0.0275–$0.110 USD per second (480p–1080p with nsfw_checker=true), $0.030–$0.120 per second (nsfw_checker=false). Wan 3.0 Prime: $0.0442–$0.182 per second (480p–1080p with nsfw_checker=true), $0.0476–$0.196 per second (nsfw_checker=false). Wan 3.0 Pro: $0.126–$0.161 per second (1080p–4K). W
Key features
Automatic model loading from Hugging Face and other sources
Hardware-aware model optimization for VRAM and context length
OpenAI-compatible endpoint
Support for multiple inference engines
Single unified endpoint for all models and machines
Distributed compute across multiple machines
Built-in app catalog with chat UIs and RAG tools
Integration with cloud providers
Video generation up to 30 seconds at up to 1080p with optional sound
Output up to 4K resolution
Browser Playground for testing without code
Request estimates before generation
Support for image and video reference inputs
One shared prepaid balance for API and Playground
Google sign-in authentication
API documentation for each model
What makes it different
No manual engine configuration needed
Automatic workload-based tuning
One endpoint covers local and cloud models
Built on trusted community engines
Independent platform not affiliated with model vendors