Ling 3.0 Flash VL: InclusionAI's New Vision-Language Model Goes Live on OpenRouter
Key Info
Ling 3.0 Flash VL, a new vision-language model from InclusionAI, is now live on OpenRouter (served by Novita Labs), adding native image/video input and advanced visual agent capabilities to the existing Ling 3.0 Flash line.
Highlights
- 124B MoE architecture with 5.5B active parameters, offering both instant and reasoning modes.
- Stronger language performance alongside native visual perception and advanced visual agent capabilities.
- Accessible now through OpenRouter's unified API, expanding the platform's growing catalog of vision-language models.