Confidential · Prepared for GoPro · Not for external sharing
ZeroGPU Video understanding demo

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 token usage for each model. The video file stays in your browser; only the sampled frames are sent.

01Footage
Drop a clip here or · MP4 or MOV
or

02Sampling
Choose a clip to see frame count and tokens.
Qwen3.6 on ZeroGPU—input tokens per frame · $0.20 in / $1.50 out per 1M tokens
Nova 2 Lite≈240input tokens per frame · $0.30 in / $2.50 out per 1M tokens
03Task

Choose a clip to start.

Your original clip plays here. Each model’s highlight reel gets its own player below.

The whole integration

OpenAI-compatible: keep your client, change the base URL and the model name.

Enter your work email to unlock the demo.