Vivix released Vivix-W1, a streaming-native multimodal video model that accepts text, image, audio and video references and lets new inputs steer the stream mid-generation. Vivix says it has ~30B active parameters and costs $0.003 per output second through Oct 31; in vendor tests an 8s 720p reference-to-video job took 8.4s on average. The API is in limited preview with standard, fast and ultrafast tiers.

Key Takeaways

  • ✓Vendor-stated ~30B active parameters with native audio-video, multi-shot and continuous streaming
  • ✓$0.003/sec promo through Oct 31 vs vendor-listed $0.080 (H3 Max), $0.112 (Kling 3.0), $0.231 (Seedance 2.5)
  • ✓Vendor test: 8s 720p ref-to-video in 8.4s avg vs 145.9s Kling 3.0 and 272.4s Seedance 2.5 (excl. queue)
  • ✓API tiers vivix-w1 / fast / ultrafast at 1/3/4 credits per second, 5–15s clips
  • ✓No third-party quality benchmark yet
Vivix launches W1, a streaming-native real-time video model: ~30B active params, $0.003/sec promo, API in preview
🖼️Official Media
Click to view high-res
🧭

Turn your technical choice into a development budget

Compare 40 dev plans & simulate token costs vs $20/mo subscriptions

⚔️ Compare Model→💰 Compare plans & limits↗
🔗

Project Links & Resources

Direct Access
Direct access to official project resources and documentation
📝
Vivix-W1 · Official post
vivix.ai/vivix-w1
↗
🚀
Vivix W1 · Product page
platform.vivix.ai/vivix-w1-model/
↗
📖
World Video Generation API · Documentation
docs.vivix.ai/video-generation/world-video-generation
↗
📖
Vivix API · Documentation
platform.vivix.ai/pricing
↗
🔬

In-Depth Technical Analysis

Vivix-W1 is a streaming-native multimodal video model (~30B active parameters per Vivix) that takes text, image, audio and video references and accepts new inputs while the stream is running, using each newly generated segment as context so the world continues rather than restarting. It natively generates synchronized audio and video, multi-shot sequences and continuous streams.

All numbers are vendor-reported: a $0.003/sec promo price through Oct 31 versus $0.080 (MiniMax H3 Max), $0.112 (Kling 3.0), $0.151 (Seedance 2.0) and $0.231 (Seedance 2.5), prices checked Oct 8. In an 8s 720p single-reference test averaged over 10 runs excluding queue time, W1 finished in 8.4s vs 10.8s, 145.9s, 183.5s and 272.4s. No third-party quality benchmark exists yet.

The API is in limited preview: upload references, create an async job, poll for video_url. Models vivix-w1, vivix-w1-fast and vivix-w1-ultrafast share quality and cost 1/3/4 credits per second; clips run 5–15s. A 5,700-credit trial pack is available and a real-time Streaming World API is marked coming soon.

Action HubReady to adopt this in production?

Benchmark side-by-side against alternatives, or calculate monthly token cost vs subscription break-even.

⚔️ Launch VS Compare→💳 View Plans↗