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.
Also, OpenAI is just a company I'd rather support than Anthropic.
While you're understandably not including the values of the $20 standard plans on both, I find the generosity of then token limits on ChatGPT plus vs Claude Pro (it's a huge difference) to be good representation of their respective attitudes towards the average user. You literally cannot use Claude pro to build real software, unless you're extremely frugal with your prompts and don't try anything even a little ambitious.
Also, Anthropic has zero models comparable to Luna.
Their responses towards using their subscriptions on opencode for one. Second, Dario just has a habit of making completely doomer comments on the future of software engieering as a job and towards the open-weights model ecosystem.
Sure, he's free to say whatever especially considering the amount of revenue he's creating, but it's just an altitude that I prefer not to see.
Sam is sketchier on a personal level, but judged just on the words coming out of their mouths, he's also much less paternalistic/controlling and more customer focused.
I think any amount of 'paternalistic/controlling' turns out to have been justified when, after dismantling the safety teams and pretending not to know what safety is, OpenAI had the HuggingFace series of scandals. You can dislike the idea of safety and people talking about safety, but not only is the evidence right there, but OpenAI came out shamefacedly and literally agreed with Amodei's statements, including that they agreed to pace the frontier.
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
elxr · · focus · HN ↗
While you're understandably not including the values of the $20 standard plans on both, I find the generosity of then token limits on ChatGPT plus vs Claude Pro (it's a huge difference) to be good representation of their respective attitudes towards the average user. You literally cannot use Claude pro to build real software, unless you're extremely frugal with your prompts and don't try anything even a little ambitious.
Also, Anthropic has zero models comparable to Luna.
bix6 · · focus · HN ↗
> Also, OpenAI is just a company I'd rather support than Anthropic.
elxr · · focus · HN ↗
Sure, he's free to say whatever especially considering the amount of revenue he's creating, but it's just an altitude that I prefer not to see.
bix6 · · focus · HN ↗
elxr · · focus · HN ↗
CuriouslyC · · focus · HN ↗
felixgallo · · focus · HN ↗
platinumrad · · focus · HN ↗
felixgallo · · focus · HN ↗