Open-source generative AI models for image, video, audio and 3D creation
One API for every top video, image and audio model, routed to the cheapest provider
Stage
Not given
Not given
Founded
2022
Not given
Based in
GB
Not given
Pricing model
Freemium
Paid
Pricing
Free for non-commercial use and for commercial use up to $1M annual revenue under Stability AI Community License. Enterprise License available for organizations with annual revenue exceeding $1M.
Seedance 2.5 from $0.06/s (480p), $0.088/s (720p), $0.210/s; Kling 3.0 from $0.09/s; Veo 3.1 from $0.20/s; Hailuo 2.3 from $0.06/s; MiniMax H3 from $0.03/s; Wan 3.0 from $0.04/s; UGC Real 1 $0.03/image; Nano Banana Pro from $0.04/image; Nano Banana 2 from $0.03/image; GPT Image 2 $0.03/image; Seedre
Key features
Stable Diffusion 3.5 Large with 8.1 billion parameters for superior quality and prompt adherence
Stable Diffusion 3.5 Large Turbo generates high-quality images in 4 steps
Model requires only 9.9 GB of VRAM to unlock full performance
Diverse outputs with different skin tones and features without extensive prompting
Generates wide range of styles including 3D, photography, painting, line art
Stable Audio 2.0 generates full tracks up to three minutes at 44.1 kHz stereo
Stable Video Diffusion transforms images into 2-second high-quality videos
Fine-tuning and customization with Query-Key Normalization for flexible base models
ControlNets for Stable Diffusion 3.5 Large including Blur, Canny, and Depth
Automatic routing to cheapest provider per request
Pay only on successful requests; failed calls cost nothing
Ready-made ad formats like talking head UGC, street interviews and product commercials
Single API key for video, image and audio models
Model Claude Agent integration via MCP
Per-key monthly budget caps
Support for uploads up to 20 MB images, 200 MB video, 50 MB audio
Results kept for 30 days; links work for 6 hours
What makes it different
Runs on standard consumer hardware without heavy demands
Highly customizable models designed for flexible base to build upon
Ownership of generated outputs without restrictive licensing implications
Leads market in prompt adherence and rivals larger models in image quality
Save up to 90% on GPT Image 2.5 compared to direct provider pricing
Only platform routing every call to the cheapest capable provider
No charge for failed requests including safety blocks and timeouts
Unified billing for 130+ models across video, image and audio in one invoice
Stability AI
VidLab