What I'm seeing with Brokk (https://brokk.ai) is that models are not really interchangeable for code authoring. Even with frontier models like GP2.5 and Sonnet 3.7, Sonnet is significantly better about following instructions ("don't add redundant comments") while GP2.5 has more raw intelligence. So we're using litellm to create a unified API to consume but the premise of "route your requests to whatever model is responding fastest" doesn't seem that attractive.
But OpenRouter is ridiculously popular so it must be very useful for other use cases!
But OpenRouter is ridiculously popular so it must be very useful for other use cases!