Vivix W1
Vivix AI's streaming-native video model for worlds that change in real time from text, voice, and motion input.
This entry is marked for review. Check the original sources before relying on its details.
Overview
Vivix W1 is a streaming-native multimodal video model for interactive video that can be steered live through text, voice, and motion. In Vivix's own 720p tests, an 8-second reference-to-video clip took 8.4 seconds on average, the fastest of the models it compared, excluding queue time. A playground and API are live, priced at $0.003 per generated second through October 31, 2026, against $0.080 to $0.231 per second listed for MiniMax H3 Max, Kling 3.0, Seedance 2.0, and Seedance 2.5. The page states no launch date; a weekly roundup places it on October 11, 2026.
This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.
Key features
- Streaming generation that responds to live text, voice, and motion input
- Vendor-reported 8.4 s average for an 8-second 720p reference-to-video clip
- API documentation at docs.vivix.ai and a playground at platform.vivix.ai
- Limited-time $0.003 per second rate through October 31, 2026
Use cases
- Interactive video and game-like experiences that change as the user acts
- Rapid reference-to-video prototyping
Pricing
$0.003 per generated second (limited-time discount through October 31, 2026); standard rate unknown.
Pricing reflects the source record and may change. Confirm current terms with the provider.
Dates and sources
- Released
- 11 Oct 2026
- Record updated
- 18 Oct 2026
- Record last checked
- 18 Oct 2026