zlacker

[parent] [thread] 4 comments
1. raw_an+(OP)[view] [source] 2026-02-04 21:22:04
Or just don’t use Claude Code and use Codex CLI. I have yet to hit a quota with Codex working all day. I hit the Claude limits within an hour or less.

This is with my regular $20/month ChatGpT subscription and my $200 a year (company reimbursed) Claude subscription.

replies(2): >>mercut+Zp >>0xbadc+gA
2. mercut+Zp[view] [source] 2026-02-04 23:45:30
>>raw_an+(OP)
Yeah, the generosity of Anthropic is vastly less than OpenAI. Which is, itself, much less than Gemini (I've never paid Google a dime, I get hours of use out of gemini-cli every day). I run out of my weekly quota in 2-3 days, 5-hour quota in ~1 hour. And this is 1-2 tasks at a time, using Sonnet (Opus gets like 3 queries before I've used my quota).

Right now OpenAI is giving away fairly generous free credits to get people to try the macOS Codex client. And... it's quite good! Especially for free.

I've cancelled my Anthropic subscription...

replies(1): >>raw_an+yq
◧◩
3. raw_an+yq[view] [source] [discussion] 2026-02-04 23:49:29
>>mercut+Zp
Hmm, I might have to try Gemini. Open AI, Claude and Gemini are all explicitly approved by my employer. Especially since we use GSuite anyway
4. 0xbadc+gA[view] [source] 2026-02-05 00:57:25
>>raw_an+(OP)
You're getting downvoted because people here don't know that the specific agent you pick can pollute your context and waste your tokens. Claude's system prompt is enormous, to say nothing of things like context windows and hidden subagents.
replies(1): >>raw_an+1H
◧◩
5. raw_an+1H[view] [source] [discussion] 2026-02-05 01:56:19
>>0xbadc+gA
I am using Codex-cli with my regular $20 a month ChatGPT subscription. Never once had to worry about tokens, request etc. I logged in with my regular ChatGPT account and didn’t have to use an API key
[go to top]