Qwen3.6-35B-A3B on ZeroGPU · vs Amazon Nova 2 Lite
Raw footage in. Highlight reel out.
Pick a clip and a sampling rate. Both models get the same frames, and you get a playable shot list, the latency, and the cost per video-hour at your settings. The video file stays in your browser; only the sampled frames are sent.
Stored only in this browser. Sent only to api.zerogpu.ai.
02Footage
Drop a clip here
or · MP4 or MOV
or
03Sampling
Choose a clip to see frame count and cost.
Qwen3.6 · — tok/frame—per video-hour, input
Nova 2 Lite · 288 tok/frame$0.311per video-hour, input · fixed 1 fps
04Task
Add your key and a clip to start.
Your clip plays here. Highlight reels play back from it.
The whole integration
OpenAI-compatible: keep your client, change the base URL and the model name.