Input-depending model on TensorFlow

I'm working on a TensorFlow model, and I would like to have different logic in the model depending on the input. My question is if it's possible to have a dispatch layer in TensorFlow that depending on the input uses one model or another?

Simplified example:

Imagine your input has two fields a: int and b: Optional[int]. This means b can be defined or not.

If b is not None you want to execute some layers, and if it's None you want to execute some other layers.

My idea was to have a dispatch layer that depending on the input executes one branch of the model or another one. Something like the architecture in the image below:

With this architecture, you'll have one only model (which is easier to deploy) with polymorphism depending on the input.

Thank you very much for your help :)