Codex on AWS bedrock bug causing 10x charges

Post by DrJokepu » Fri, Aug 21, 2026, 4:46 AM UTC

amluto wrote: post #5

Wow, that whole thread is borderline incoherent, presumably generated by an AI without adequate oversight. Here are the docs: https://developers.openai.com/api/docs/guides/prompt-caching... The thread has little explanation as to what weird thing they’re doing to Codex that is making the default work poorly, and it kind of seems like it’s getting confused about whether it wants to set the caching mode or the breakpoi…

Post by the_duke » Fri, Aug 21, 2026, 4:56 AM UTC

otterley wrote: post #4

TheP1000 wrote: post #2

Our codex on AWS Bedrock read / write cache ratio was less than 5%. Cache writes are very expensive and they were never being used. This results in codex on Bedrock causing ~10x what it should due to no caching and massive writes. The workaround in issue resolved for me: web_search = "disabled"

If you’ve got a workaround, I’d suggest updating the issue description to have it up top there so similarly impacted users can spot it quickly and benefit.

Post by zx8080 » Fri, Aug 21, 2026, 5:05 AM UTC

DrJokepu wrote: post #12

amluto wrote: post #5

Wow, that whole thread is borderline incoherent, presumably generated by an AI without adequate oversight. Here are the docs: https://developers.openai.com/api/docs/guides/prompt-caching... The thread has little explanation as to what weird thing they’re doing to Codex that is making the default work poorly, and it kind of seems like it’s getting confused about whether it wants to set the caching mode or the breakpoi…

> It sounds to be like 5.5 and below may have been using a conventional attention scheme where a cached KV sequence can be easily used to restore a prefix of itself, but perhaps 5.6 is using linear attention or LSTM or another recurrent scheme where you cannot rewind the model state by just truncating it. I feel like this is the kind of substantial change to your product that you would need to tell your customers abo…

Post by hahuhs » Fri, Aug 21, 2026, 5:18 AM UTC

Post by otterley » Fri, Aug 21, 2026, 5:36 AM UTC

the_duke wrote: post #14

otterley wrote: post #4

Earlier quoted context omitted.

If you’ve got a workaround, I’d suggest updating the issue description to have it up top there so similarly impacted users can spot it quickly and benefit.

It's already mentioned in the issue...