Hacker News Reader

Comment by paxys | Hacker News Reader

How is $5/day irrelevant? In the $150/mo range you can get effectively unlimited usage of GPT 5.6 Sol (Pro plan). Why use a much weaker model for the same price?

View on HN

> In the $150/mo range you can get effectively unlimited usage of GPT 5.6 Sol

With 5 active sessions going nonstop? That seems like a pretty important qualifier.

Others have said similar but I disagree, I'm spending $200/m and I can easily burn through my weekly quota with a few overnight goals using 5.6 medium.

And what do you do with all that?

5.6 medium is pretty good at implementing moderately complicated things as long as you've done a good job specking out the types and the API contracts and acceptance criteria.

I can pretty easily burn through my weekly quota over several agent coding hours with minimal supervision when tasked with some pretty large but well-planned refactors.

I've reverse engineered multiple classic games and turned them into popular, browser-based MMO-like experiences.

I'm also creating a free platform that replaces extremely out-of-date software, some of it only available with mutli-million dollar contracts, to help medical physics professionals with cutting-edge radiotherapy devices used to treat cancer.

https://brynnbateman.com/ for a list of projects

An MMO of Full Throttle would be amazing!

It'd be interesting to see what someone could do to turn a 90s era adventure game into an MMO! I never played the game myself but I think basically any game dev project that modernizes stuff is really neat.

Time to make creative software for linux that can replace adobe for Video/photo editing :P

GIMP isn't bad these days, I use it constantly

Nice! I tried to play https://eternalsagas.com/play but it stalls at 45% loading with the progress bar always at 0 but the music playing.

And out of curiosity, how do you automate testing the porting in the browser that's actually playable etc? And aren't you a bit scared of hosting and serving the "hairy bits" such as full assets? Nice job anyway!

Yeah that's my weakest browser game since I've actually transitioned to using a desktop Godot client I haven't released yet. It will load eventually it just takes forever bc the assets are quite large, which is part of the reason I've had to move to Godot. That project doesn't exactly have an active user base which is why it's lower on priority list to fix.

I automate testing playable parts in browser by adding a dev mode that allows text commands for everything instead of having to rely on clicking UI or 3D elements. It can see the full game state in JSON and interact in any way via commands.

And re: IP - I just accept that I might get a C&D any day and have to take it all down. I'm careful to not accept a single penny for any reason and don't even have Patreon. Usually monetizing is what makes IP owners unhappy. And for the Pokemon MMO I just don't advertise it anywhere meaningful since they'll C&D the second they see it. Largely made it for my nephew and we play it together.

Same here with Claude Opus on 20x Max plan. Easy to burn through with 3-5 parallel sessions, each with their own subs going.

Then, once I go over, API pricing racks up FAST!

I burned through $100 of credits in literally 40 minutes doing the same long running task I always do.

not at all true. if you're truly using it across the board for smaller things (translation of pages, filtering of every individual tweet based on its relevance to you etc), the costs ramp up super quickly.

i used for work where i did less and it quickly reaches thousands if you're not careful. i can already see what some will say: skill issue et cetera - whatever.

I thought it went without saying that GPT 5.6 Sol is the wrong model to use for things like filtering tweets. Apparently not?

If you factor in cost then it may well be, but it's definitely the case that the high-end models can get you significantly better results than the cheaper models even for tasks that feel like they should be straightforward.

You would think that no one would be stupid enough to use Fable or Sol for small one-off tasks like filtering tweets, but AI has opened up a lot of avenues for stupid people to ship code. It's only going to get worse.

yeah man it's me who's stupid and not you when i use an example of the author who claims that you can use pro subscription on all of the mundane tasks w/o going over the budget. sure. my point is that you can only use it with cheaper models. also some tweets are fairly dense in their compression/context, so yeah sometimes it's necessary.

$100-200/mo is the subscription price. You aren’t going to go over. And you can select smaller models as well. Not everything has to be done by the most expensive one.

You just get throttled, which interrupts your whole workflow.

>> you can get effectively unlimited usage of GPT 5.6 Sol (Pro plan). Why use a much weaker model for the same price?

> Not everything has to be done by the most expensive one.

Ok then.

I really doubt that the either of the pro plans are subsidized heavily enough to support you swapping v4Flash for Terra, much less Sol.

$5/days is ~330 Mtok/day, that’s a nontrivial amount of work, and none of the gpts are more efficient than deepseek at $/task if deepseek meets your quality bar.

They do give a significant amount more than you would expect from the API pricing. The US provider API pricing has heavy margins by all accounts (and most are short enough of GPUs that there's little incentive to drop).

5 USD is at the "raw" API price.

OpenCode currently offers 60 USD API credits at 10 USD per month (OpenCode Go) and have even doubled it temporarily as a promotion.

Effectively you can get Deepseek for 1/12th the already ridiculous cheap API price.

From here, it looks like opencode is hemorrhaging money. I've got a Opencode Zen free account, and I've been using deepseek-v4-flash-free on Pi for a bit, and I haven't hit a limit yet. Sometimes my request fails, but retrys work. I know this is a very cheap model, but it's being given out for free. I assume they might be training on outputs?

Those are not at the same price. Opecode’s 60 USD of deepseek usage is charged at much higher rates than what deepseek themselves charge at.

> Opecode’s 60 USD of deepseek usage is charged at much higher rates than what deepseek themselves charge at

Per the open code zen pricing page[1], it appears that the token prices are the same, but their cache is 10x more expensive?

[1]: https://opencode.ai/docs/zen/#pricing

Flash Opencode 0.14/0.28/0.028

Deepseek 0.14/0.28/0.0028

Pro Opencode 1.74/3.48/0.145

Deepseek 0.44/0.87/0.0036

For flash the input/output is the same, but the cache difference is big, you're paying 10x on >95% of your tokens.

For Pro, it's even worse, input/output is 4x and cache is 40x. The price different is really brutal. Yes you will still come out ahead by spending your first 10$/month on opencode go, but you will be saving a lot less than initially appears from their (60 USD for 10 USD pitch).

[0]: Deepseek: https://api-docs.deepseek.com/quick_start/pricing/ [1]: Opencode: https://opencode.ai/docs/zen/#pricing

> In the $150/mo range you can get effectively unlimited usage of GPT 5.6 Sol (Pro plan)

Not true. Sol on XHigh or Max runs out even on the $200/mo plan. It's not close to effectively unlimited. Maybe at 2x the current allowance it can.

What are you doing where you're getting Sol on XHigh or Max to run out on the $200 plan? Last night, I had 48% of my weekly limit left, so I spun up 4 projects I had been working on and ran them all on Ultra with Fast mode and /goal, and it took over 4 hours to burn through that. I mean, I was reeeeally trying to use it up because I just can't use it up with normal usage for weekend and after-work programming. I've had Max crunching on something this morning for 3 hours now and I've only used 4% of my weekly limit ...

> What are you doing where you're getting Sol on XHigh or Max to run out on the $200 plan?

Real work. $200 looks good on the outside until the essence of it, e.g. the models lie. I gave a list of spec to Sol and Sol decided some items didn't need to be done and the reason was "unproven", "not enough evidence", etc.

They all come up with amazing ways to lie (or be lazy). Often times what you get isn't what you asked for (only on the surface). E.g. I ran it to iteratively bench and optimize a better data structure for the project. It spent hours and finally came up with something. When I check it out -- it benchmarked the wrong criteria and was way off. So here we go again. Most AI work looks good on the surface. There are infinite edge cases.

So to do real work and gate it you need to:

1. Plan

2. Get it to do the work

3. Get independent agents to check from different angles

4. Take that feedback and get it to fix those gaps

5. Match against the plan and redo parts if needed

Every task is easily 4-5x the estimated amount of tokens.

p.s. well I did burn some banked resets building a compiler for some language AND it is still NOT done. Every time it says done I say check it says ok we still have bugs...

The cost per token is super low. If you're used to paying OpenAI or Anthropic API-based fees then the same workload on DeepSeek feels free.

Ignoring the other side of the equation is a pretty wild thing for you to do here:

> I'm running it in Oh My Pi with a second instance running as "advisor" and even with 5-6 active sessions (effectively 12 streams)

$5 a day is pretty extreme in DeepSeek. You really have to abuse it to get anywhere close to it. Maybe something in around hundreds of millions of tokens per day, considering cache hits and all.

And to be frank, it is not that much weaker for regular software development work. I use Claude at work and I see no difference in capability. I only notice a dramatic difference in how much more expensive it is.

Reply on news.ycombinator.com