Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Codex Resets

codex-resets.com

Post reply on HN
Print view View original

51–60 of 214 posts

Re: Codex Resets

#51

Post by slopinthebag »

Aurornis wrote: post #46
slopinthebag wrote: post #37

Earlier quoted context omitted.

$10,000 in less than three weeks is incredible. The bean counters sure have a blind spot for AI…

That’s less than the fully loaded cost of hiring another engineer. If someone is making the case that it’s helping the team get twice as much work done without hiring more people (which I’m neither agreeing with or disagreeing with) then the bean counters would actually prefer it. Hiring people is messy and expensive. Spending on API costs is a dial that you can turn down later if you need to, without laying anyone o…

Well someone would actually have to make that case. So far nobody has been able to.

Re: Codex Resets

#52

Post by slopinthebag »

Aurornis wrote: post #43
huey77 wrote: post #15

Crazy value for money now with the banked resets. At my $COMPANY, we have claude enterprise at API pricing. I've blown through $10k already this month, opting for Opus 4.8 w/ Sonnet 5 agents where possible. On my codex pro plan, I am 5.6 sol'ing my way everyday with the odd ultra mode. Point being my real API usage here must be very unsustainable!

> Point being my real API usage here must be very unsustainable! I think it’s funny that everyone anchors to the API pricing as the real cost. Most likely is that their API costs are printing profits. They can sell the subscription plans at a slight loss because it gets more people like you hooked on GPT models at home and suggesting them at work, where the real money is made. I think their subscription plans go most…

Idk, Kimi K3 is not that much cheaper than Opus and it’s probably a smaller model. We’ll know for certain when commodity providers price it, but I expect it to be the same price.

Re: Codex Resets

#53

Post by ssl-3 »

minimaxir wrote: post #39

I really wish there was a canonical platform endpoint to programmatically check Codex usage amount and the quota reset times so I could just vibecode an app to alert "hey, your usage just went to 100% so that means OpenAI did a reset" and "hey, your 5-hour usage is at 10%, wrap up what you're doing". The only way to do it now is through shenanigans with the Codex App Server which is not ideal.

The 5h limit is gone (for now). It does not presently need to be chased. :)

For the automated checking of other stuff: It was a one-shot prompt to get Codex clank up some Python that returns remaining usage, next reset time/date, and so on.

The result does use Codex App Server, but it's a short-lived process that is dealt with over stdio so that's... fine-ish, I guess?

Re: Codex Resets

#54

Post by bottlepalm »

sumedh wrote: post #44
bottlepalm wrote: post #12

It’s like two parents fighting over their children with who can give them the most gifts. I’m loving it, two Christmases!!

Ant is not giving lot of gifts though :(

My /usage is telling me '+50% weekly limits promo through Aug 19' - that's huge, and better than what I'm getting with the equivalent Codex plan I have right now. Though what Codex does have over Claude is Sol /fast - that hands down is the best coding experience right now.

Re: Codex Resets

#55

Post by Lwrless »

Those resets and the removal of the 5-hour usage limit are quietly anchoring me to a much higher usage baseline. I've stopped rationing and just spawn a bunch of agents to work at whatever pace I want, because there always seem to be more resets on the way (at least true for the last week). And now I am actually worried about that if one day they just stop doing so, my "normal" workflow will suddenly exceed the limit, and upgrading will feel like a step backwards.

Re: Codex Resets

#57

Post by sebjones »

huey77 wrote: post #15

Crazy value for money now with the banked resets. At my $COMPANY, we have claude enterprise at API pricing. I've blown through $10k already this month, opting for Opus 4.8 w/ Sonnet 5 agents where possible. On my codex pro plan, I am 5.6 sol'ing my way everyday with the odd ultra mode. Point being my real API usage here must be very unsustainable!

My usage sky rocketed with GPT 5.6 sol thanks to all these resets. I'm pretty sure this is not sustainable for me.

Re: Codex Resets

#58

Post by enraged_camel »

midnightbobarun wrote: post #36

I'm kind of impressed how often they manage to do this. Claude Code and Grok Build do resets too, but nowhere near this often. And in an ironic twist for a big company with the infrastructure, Google Antigravity never seems to do resets like this at all (at least that I've noticed). I wonder how much this stuff costs OpenAI to do?

They can do it often because they have compute, and they have compute mostly because they are pretty far behind Anthropic when it comes to heavy enterprise users. They’ve supposedly added several million since 5.6 launch, which is a steep growth curve. We will see if those users stick around. Anecdotally, I’ve stopped using it for anything major because it has attempted to do some very unsafe things when I wasn’t looking. Friends I’ve talked to have also gotten over the initial honeymoon period.

Re: Codex Resets

#59

Post by sebjones »

Lwrless wrote: post #55

Those resets and the removal of the 5-hour usage limit are quietly anchoring me to a much higher usage baseline. I've stopped rationing and just spawn a bunch of agents to work at whatever pace I want, because there always seem to be more resets on the way (at least true for the last week). And now I am actually worried about that if one day they just stop doing so, my "normal" workflow will suddenly exceed the limit…

All these resets are given because of rival competition. When they win the market, we are going to be squeezed $$$.

Re: Codex Resets

#60

Post by sebjones »

mvkel wrote: post #5

> 5 days ago: 7M users > 4 days ago: 8M users > 3 days ago: 9M users That's some incredible growth.

I was thinking about this. How do they measure this? Every upgrade of the ChatGPT apps get counted?
Post reply on HN