Today we're launching Sonic Inference Pods, our network of modular data centers built for AI inference.
Each one delivers 1MW of compute from a 20-foot shipping container, deployed wherever there's power.
Learn more: bit.ly/4hNdg9I
Two new Ideogram models are now on Runware 🎨
@ideogram_ai 4.0q 9.3B, open-weight model:
- Quantized V4.0, running on Runware’s hardware
- Bounding-box layout control for precise text and element placement
- Accepts structured JSON prompting for repeatable output
- Color-palette
FLUX Video Upscale is now on Runware 🎬
- @bfl_ai's FLUX 3 powered super-resolution upscaler
- Video inputs upscaled to 1080p, 2K, or 4K
- Up to 3x upscale factor
- Precise & Creative modes
- Input audio tracks preserved
Seedance 2.5 1080p is now on Runware 🎬
Seedance 2.5 now generates native 1080p on Runware. Full HD video from the API, no post-generation upscaling required.
Our pricing is built different.
Seedance 2.0: $0.16/s at 720p.
Seedance 2.5: $0.2304/s at 720p.
Same prompt across both models. Draft on 2.0, render final on 2.5. Same API call either way, so switching is a parameter change rather than an integration.