Bedrock has been fine throughout today; just pick two providers and you have much more stable Claude :)
Also, sometimes older models work fine, Opus 4.8/4.6/4.5 are worth trying.
I would go as far as saying they are sometimes better than the newer ones! It is impressive that Opus 5 can one-shot a complex website, but it is very annoying if I only asked it to write tests.
Last week, I asked Sonnet 5 to add one line to the documentation, commit, and push. Ten minutes later, I discovered it embarked on a side quest of exploring my whole Git history, different branches, etc.
If you are a solo developer who has the patience to tinker endlessly, this advice is probably fine.
If you are responsible for provisioning AI services in a team setting, this advice starts to fall apart rapidly. OAI and Anthropic might as well be oil and water when it comes to what tools and descriptions are most ideal.
Swapping the inference provider like it's some interchangeable module is a total fantasy in most real world settings.
> Also, sometimes older models work fine
> sometimes
My users are hoping for slightly more definitive results. "Usually" or even "often" would be much preferred.
I'm not saying that works in every business or billing scenario, though.