novita
via Hugging Face- Input
- $0.075
- Output
- $0.22
Scores appear here when an evaluation matches this exact model.
Switch reasoning on or off; hybrid linear attention and multi-token prediction support long-context self-hosted inference.
The multimodal version built on Ling-3.0-flash — 124B total / ~5.5B active per token, with native text, image, and video understanding. It’s mainly designed for multimodal agentic workflows, long-context…