Lowest-cost model API platform.
Run production image and video models through one API. Adaptive scaling and Flash Switch routing keep GPU utilization high and prices low.
API
output
final_image
{
"task_type": "single_image_edit",
"resolution": "1024x1024"
}
image/text_to_image
Omni Image AIO
omni / omni-image-aio
From 1 credit per image task
可用
Production image generation and editing runtime for text, single-image, and dual-image workflows.
text_to_imagesingle_image_editdual_image_edit
API
output
final_video
{
"task_type": "text_to_video",
"duration": "4s"
}
video/text_to_video
Omni Video AIO
omni / omni-video-aio
From 6 credits per video task
可用
Video generation and transformation runtime for text, image, first-last-frame, and video-to-video jobs.
text_to_videoimage_to_videofirst_last_frame_to_videovideo_to_video
Adaptive scaling
Model groups expand and contract against real demand instead of fixed idle capacity.
Flash Switch
Fast model switching raises utilization across image, video, and future model groups.
Low-cost supply
Production APIs run on efficient consumer-side GPU platforms whenever quality allows.