[wongarsu]

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

[rvnx]

The main thing about Openrouter is also that they take 100% of the risk in case of overcharges from the models, you have an actual hard cap.

The minus is that context caching is only moderately working at best, rendering all savings nearly useless.

[largbae]

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?

[SR2Z]

Is there any risk? Don't the model providers also bill by the token?

[fuzzy2]

The accounting could be asynchronous, so you could overshoot your budget by a few requests before you're blocked.