💸 Has a provider spend limit ever switched off your AI features mid-month?

I was reading up on API spend limits for a post, and one detail stuck with me.

On Anthropic’s standard tiers there’s a monthly spend cap ($500 on the lowest). When you hit it, requests come back as a 429 that looks like a rate limit, but with no retry-after header. Automatic retries just keep failing until the 1st. OpenAI’s hard spend limits return 429s too.

Run it on an ordinary month: $280 spent by day 10, about $32 a day. That crosses a $500 cap on day 17. The invoice would have said around $920, but the app stops working almost two weeks before anyone opens it.

Do you know which day your app would hit its limit, or do you find out when users start reporting errors?