Ling-3.0-flash-Fin launched on OpenRouter

OpenRouter has launched inclusionAI's Ling-3.0-flash-Fin financial enhancement model and provides a free access point for it.

Its base version, Ling-3.0-flash, employs a hybrid expert architecture with 124 billion total parameters and 5.1 billion activation parameters, targeting inference, long context, and agent tasks. Publicly available information on the financial version is currently limited; therefore, this article only confirms the model entry point and infrastructure information on OpenRouter.

refer to:OpenRouter Model Page、Basic model card