FallbackModel to allow model_settings specific to each model

[svilupp]

Description

Publishing here as a continuation of the conversation on Slack.

Currently, FallbackModel only accepts a list of model instances (or names) and a fallback_on predicate, but there’s no way to supply different ModelSettings (e.g. thinking_config) per model.

That means if you want to use, say, Gemini 2.0 Flash (which doesn’t support a thinking budget) and Gemini 2.5 Flash (which does), you cannot configure each individually—you can only pass a single model_settings at the Agent or run call level (which applies to all fallback models).

This leads to failures when the first model in the fallback chain doesn’t support settings required by the second (and vice versa).

References

FallbackModel

[DouweM]

@svilupp Thanks for the issue. I think we'll want to add a settings field and __init__ argument to Model, so that you set separate settings on each model instead of needing to pass them to the Agent (or one of the run/iter methods). That model.settings field can then be taken into account here:

pydantic-ai/pydantic_ai_slim/pydantic_ai/agent.py

Line 673 in 49658f3

model_settings = merge_model_settings(self.model_settings, model_settings)

Would you be up for filing a PR to that effect?