At this point, the deciding factors for me between Claude Code 20x and Codex Pro 20x are:
1/ Usage limits: downstream of input/output cost, but resets and obscure windows and odd 20x plan / 5x plan != 4x usage math throw a wrench into it. Winner right now is Codex by a mile, especially when you factor in the fact that ChatGPT usage (even 6 Astra Pro) is essentially unmetered on the 20x plan. Always a bummer when asking if I should see a doctor about a rash means I can't code as much. It's also is a godsend if you use an MCP like oracle to automate the process of calling the Pro model on particularly tough problems, giving better planning results or deeper code analysis without burning usage.
2/ Context window in the harness. Claude Code wins on this. There used to be a toml file workaround for Codex to extend the GPT context window to 1m, but this stopped working on the plans and only on per-token billing (ETA: noname120 pointed out this is no longer the case and it can be enabled again [1]). 252k is just not enough. Codex's compaction is very good, fwiw, but it happens so frequently that even a model as powerful as Astra sometimes loses the plot on long-running tasks.
3/ Ability to use the plan outside of the official harness. Codex wins. Anthropic does shit like bills requests as extra usage if it sees a hermes.md in a commit.
I've subscription hopped a bunch, and at times I've had both, but I keep coming back to Codex because it wins on 2/3.
ETA: apparently I haven't been Keeping Up With the Altmans and new 20x signups have been disabled for a few weeks. I am grandfathered in, which makes the comparison above pretty much moot.
What are you talking about? ChatGPT unmetered? No way! That was 2 months ago perhaps and it’s possible your account still hasn’t gotten the new limits. I noticed around 1 month ago I was still going full throttle on my codex subscription and my limits were barely budging, and then all of sudden people around me started to complain about limits. I thought they’re crazy, but then my account go the hammer, and that was it. If I have the same pattern of usage like I did before, basically having an agent working continuously on a coding take, my weekly limit goes in 2 days.
Interesting, rolling out new limits would explain a lot. Where did you hear this? I wonder if they detect users with multiple accounts and do that first.
It’s all anecdotal based on my experience and other countless discussions I have seen online. I’ve heard speculation that once they hit 20 million codex users capacity is tighter so they have to manage it. The previous limits were unsustainable compared to token pricing.
On usage in ChatGPT settings, I see:
Plan limits
Shared across Codex, Work, Workspace Agents, and ChatGPT for Excel. Chat conversations are not included.
Is this not the default anymore? I am on the (now closed) 20x plan.
That’s the default. I didn’t express myself clearly but I thinking your situation is not the common case anymore, or perhaps you are not using it hard enough. Codex limits deplete very fast these days, it’s not “unlimited”.
I am saying that because ChatGPT usage is unlimited, I don't have to eat into my Codex limits when I use ChatGPT. Codex certainly has limits. Last time I had a Claude sub (hedging here since much of the info in my comment was outdated), my usage limits on claude.ai threads was shared with Claude Code.
jeffnash · · focus · HN ↗
1/ Usage limits: downstream of input/output cost, but resets and obscure windows and odd 20x plan / 5x plan != 4x usage math throw a wrench into it. Winner right now is Codex by a mile, especially when you factor in the fact that ChatGPT usage (even 6 Astra Pro) is essentially unmetered on the 20x plan. Always a bummer when asking if I should see a doctor about a rash means I can't code as much. It's also is a godsend if you use an MCP like oracle to automate the process of calling the Pro model on particularly tough problems, giving better planning results or deeper code analysis without burning usage.
2/ Context window in the harness. Claude Code wins on this. There used to be a toml file workaround for Codex to extend the GPT context window to 1m, but this stopped working on the plans and only on per-token billing (ETA: noname120 pointed out this is no longer the case and it can be enabled again [1]). 252k is just not enough. Codex's compaction is very good, fwiw, but it happens so frequently that even a model as powerful as Astra sometimes loses the plot on long-running tasks.
3/ Ability to use the plan outside of the official harness. Codex wins. Anthropic does shit like bills requests as extra usage if it sees a hermes.md in a commit.
I've subscription hopped a bunch, and at times I've had both, but I keep coming back to Codex because it wins on 2/3.
ETA: apparently I haven't been Keeping Up With the Altmans and new 20x signups have been disabled for a few weeks. I am grandfathered in, which makes the comparison above pretty much moot.
[1]<a href="https://news.ycombinator.com/item?id=49806060">https://news.ycombinator.com/item?id=49806060
lifty · · focus · HN ↗
nwienert · · focus · HN ↗
lifty · · focus · HN ↗
jeffnash · · focus · HN ↗
Is this not the default anymore? I am on the (now closed) 20x plan.
lifty · · focus · HN ↗
jeffnash · · focus · HN ↗
lifty · · focus · HN ↗
jeffnash · · focus · HN ↗