Comment by edg5000

2 days ago

> eat the losses

Look at your token usage of the last 30 days in one of the JSON files generated by Claude Code. Compare that against API costs for Opus. Tell me if they are eating losses or not. I'm not making a point, actually do it and let me know. I was at 1 million. I'm paying 90 EUR/m. That means I'm subsidizing them (paying 3-4 times what it would cost with the API)! And I feel like I'm a pretty heavy user. Although people running it in a loop or using Gas Town will be using much more.

2 comments

edg5000

dudeinhawaii 2 days ago

I just ran some numbers and it works out if you're a prolific user.

Over 9 days I would have spent roughly $63 dollars on Codex with 11.5M input tokens plus 141M cached input tokens and 1.3M output tokens.

That roughly mirrors the $100-200/wk in API spending that drove me to the subscription.

  | Category | Tokens | Rate (/1M) | Estimated Cost |
  |---|---:|---:|---:|
  | Input (uncached) | 11,568,331 | $1.75 | $20.24 |
  | Cached input | 141,566,720 | $0.175 | $24.77 |
  | Output | 1,301,078 | $14.00 | $18.22 |
  | Total | 154,436,129 | — | $63.23 |

BUT... like a typical gym user. This is a 30/d window and I only used it for 9 days, $63 worth. OpenAI kept the other $137.

It makes sense though for heavy use.

edg5000 2 days ago

My hopes are on harness engineering allowing cheaper (but still large) models to shine. I'm evaluating DeepSeek because it would allow insane agent armies. Although DeepSeek charges for thinking tokens, something easy to overlook.
DeepSeek has the tendency to think... a lot!. Without a good harness I can't evaluate it well; time will tell.
OpenAI doesn't; it's embedded into the price, I think.
Cheap = we can run 10x the workloads, bigger imagination = innovation. Maybe 10 dumb agents in a loop can beat 1 Opus? Haha.