A lot of inference providers for open models only accept prepaid payments, and managing multiple of those accounts is kind of cumbersome. I could limit myself to a smaller set of providers, but then I'm probably overpaying by more than the 5.5% fee
If you're only using flagship model providers then openrouter's value add is a lot more limited
I haven't noticed any problems with large context requests through OR to e.g. Opus (other than the rate at which my budget gets spent!). Is this a performance thing?
If you're only using flagship model providers then openrouter's value add is a lot more limited