Barry Coleman

Credits look like a solution to variable cost. They're really a way of moving the variance onto the user without telling them.

In Arteza a quick edit and a full multi shot render are about 12x apart in what they cost us to run. Both are priced in the same unit. So someone learns an exchange rate from the cheap action, builds a mental model, then spends a third of their balance in one click and feels robbed. That isn't a pricing bug. We asked them to hold a cost model in their head that we never showed them.

What's worked is putting the credit cost on the button before the click instead of in a docs table. Boring fix, and it cut the where did my credits go messages more than any price change we made.

The part I haven't solved is failures. A bad output still burned the compute. Refund it and people retry until they like the result. Don't refund and credits feel like a slot machine. We refund and eat it, which won't scale.

Let me know if this sounds familiar:

Me: Implement issue ABC and satisfy every acceptance criterion in the spec.

Adding AI features to indie products often brings unexpected API cost spikes. I ve been testing user-level rate limits, token quotas and cached responses to keep spending predictable.

I m curious to hear practical approaches from other builders:

1. Do you enforce hard monthly caps for every user?

2. What fallback workflows do you offer once AI quotas are exhausted?

3. Which caching strategies work best for repeated AI requests?

Many generic guides skip these operational details, so real production experience would be really helpful.