Unverified50% confidenceFactExact time
The Workers AI documentation notes audio at about 780 tokens per minute, and video at up to about 15,400 tokens per minute at the highest resolution (about 8,600 at 480p); at $0.15 per million, one minute of highest-resolution video with sound comes to about a quarter of a cent.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/12/2026
First Seen
Valid until: 10/26/2026
Sources
Related Entities
Related Claims
UnverifiedIn video generation, the computational cost of self-attention is proportional to the square of the number of tokens; after VAE encoding and patching, a 4-second 720p 24fps video can yield tens of thousands to over a hundred thousand tokens in total.72% similarUnverifiedLocal deployment of mainstream AI video generation models typically requires a dedicated graphics card with at least 8 GB of VRAM (NVIDIA RTX 3060 or above), while higher resolutions or longer durations require 16 GB or 24 GB of VRAM.65% similarUnverifiedIn testing, a video with 1344P resolution and 15 seconds duration was generated, containing both visuals and audio.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1011208API
curl https://kongchang.com/api/v1/knowledge/claims/1011208MCP
get_claim(id=1011208)