How to Install / Upgrade: Ling 3.0 Flash is now available on AI Gateway

Title: Ling 3.0 Flash is now available on AI Gateway

Ling 3.0 Flash from Ant Group is now available on AI Gateway. It is a Mixture-of-Experts model with 124B total parameters and about 5.1B active per token. It has a 256K token context window and runs in thinking and non-thinking modes. It is built for token-efficient agentic inference at production scale.

To start using it, open AI Gateway and select Ling 3.0 Flash as the model for your requests. Point your existing AI Gateway traffic or new agent workloads at this model instead of your previous choice. Use thinking mode when you want the model to reason step by step, and non-thinking mode when you want a direct answer. Keep the free window in mind: the model is free to use for the next three weeks, through August 3rd.

Confirm you are calling the model through AI Gateway and that the selected model name is Ling 3.0 Flash. After August 3rd the free period ends, so check billing or plan settings before relying on free usage past that date. Verify both thinking and non-thinking modes if your app needs both, and watch token use against the 256K context window so long agent runs do not overflow.