Model Cadence
Plus $4/mo

CogVideoX-3

Z.ai · Released Jul 15, 2025 · Closed weights

Video generation model for text-to-video, image-to-video, and first/last-frame clips with optional sound effects

Context window
512
tokens
Lab announcement ↗Open in the timeline
BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

Z.ai's past year

12 release days in the past year, about one every 30 days. The next is expected around Nov 18, 2026. Forecasts ↗

NovDecJanFebMarAprMayJunJulAugSepOctNov

Specifications

RELEASE DATEJul 15, 2025
WEIGHTSClosed weights
CONTEXT WINDOW512
MAX OUTPUT0
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext, image/png, image/jpeg
OUTPUTSvideo/mp4

Models.dev record ↗

Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.