| ▲ | joshstrange 5 hours ago |
| > 50% cheaper cache than GPT-6 Sol will get you far more mileage on Codex. Cache doesn't help you much when you are compacting every 5 minutes... I was shocked at how quickly I ran out my $100/mo subscription with a single agent (sol medium). |
|
| ▲ | redox99 4 hours ago | parent | next [-] |
| If you run out of sol medium with $100 you're doing something wrong. Astra destroys your usage, I get 1 day of usage with Astra, but 6 sol is almost unlimited and I only use xhigh. |
| |
| ▲ | Aeolun an hour ago | parent | next [-] | | It’s only nearly unlimited if you haven’t just used a banked reset. After a banked reset your weekly usage gets cut by about 80% (not the week you need to wait to get your normal limits back though). ChatGPT has given me a really good reason to cancel. | |
| ▲ | jorblumesea 3 hours ago | parent | prev | next [-] | | yeah I use sol constantly and have done maybe $15 of spend in the past week. it's solid and cheaper. this is at least 4-5 investigations, prs, whatever per day. | |
| ▲ | shimman 4 hours ago | parent | prev [-] | | "You're holding it wrong." Is hardly a retort from a real paying customer having problems with their paid services. This is why these companies are struggling to make money, they're chastising their customers just like they've been chastising the human race. | | |
| ▲ | trio8453 an hour ago | parent [-] | | > "You're holding it wrong." Is hardly a retort from a real paying customer having problems with their paid services. It's very appropriate in the cases when you're holding it wrong. The fact that you're paying doesn't mean that you can't make mistakes or waste resources. |
|
|
|
| ▲ | onlyrealcuzzo 3 hours ago | parent | prev | next [-] |
| If you're compacting every 5 minutes, you have a workflow problem - period. No LLM will be cost effective if it's compacting this often. You have to find a way around it. |
| |
| ▲ | ngruhn 3 hours ago | parent [-] | | Context window is only 275k or something. And honestly compaction is not that bad in Codex. I often don't even notice I went through 5 compactions in a session. | | |
| ▲ | onlyrealcuzzo 13 minutes ago | parent | next [-] | | If it's compacting every 5 mins, you're going to notice it in your cache miss ratio and your costs... It also presumably means it's regularly not able to get everything it wants to have to make decisions in context, which means it's going to perform poorly... | |
| ▲ | jeremyjh 15 minutes ago | parent | prev | next [-] | | I don’t usually have a problem doing a complete task in that context size. OMP does make a lot of use of rewind which may be helping - basically forks itself and sends back a summary after a long tangent. Coding tasks use a Luna max agent. I’ve also found compaction not to be a problem when it does happen. | |
| ▲ | SyneRyder an hour ago | parent | prev | next [-] | | Sounds like that's the problem then, 275k is a tiny context window. I regularly have sessions that go to 450k or even up to 700k for an unattended overnight Claude Opus session. Apparently OpenAI makes you manually setup their 1 Million context window, and it seems to be only documented on X: https://x.com/thsottiaux/status/2089082893804896524 There's at least a forum thread about it here: https://community.openai.com/t/why-does-codex-report-a-258-4... | | |
| ▲ | gf000 23 minutes ago | parent [-] | | But that 250k context worth way more than 1M in terms of how well it's utilized, so actually I do like codex trying to keep you at that sweet spot. |
| |
| ▲ | sally_glance 2 hours ago | parent | prev [-] | | Same for me, I started wondering if maybe workflows using compaction instead of clear + markdown memory would be more efficient. Writing a plan or tasks to a file often has the next session repeat part of the exploration, compaction seems to keep most relevant context. |
|
|
|
| ▲ | manmal 2 hours ago | parent | prev | next [-] |
| Your tool calls (MCPs?) are very likely too wasteful. Apply some filtering logic on the offending tool’s output. Either a wrapper CLI, or just tell codex how to filter. |
|
| ▲ | AmazingTurtle 3 hours ago | parent | prev | next [-] |
| you can actually leverage 400k and 1M contexts in codex with very little code changes to the harness. note that excess context past the.. 250k or 400k mark (i don't remember) is charged at 2x the price. |
|
| ▲ | apitman 4 hours ago | parent | prev | next [-] |
| You have a lot of control over compaction, both directly by changing compaction settings, and indirectly by how you structure your codebase/docs so agents use less tokens. |
|
| ▲ | codewithcheese 5 hours ago | parent | prev | next [-] |
| you can config codex to compact at a higher context limit |
|
| ▲ | _davide_ 4 hours ago | parent | prev | next [-] |
| As a reference i burn 1% percent for every 40 minutes of sol on average |
|
| ▲ | antonvs 4 hours ago | parent | prev [-] |
| Try Gemini. It’s so cheap I often use my personal AI Pro account for corporate work, and most of the time it doesn’t matter. |
| |
