Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🚨 codex users!! this is what you are getting for $20 GPT-6.1 Sol at Max (using fast) > 37 Million tokens > 53 Minutes of work > 48% of your WEEKLY usage!!! > $18 API usage Its EXTREMELY SLOW on normal The worst part is you are only getting...

57,436 Aufrufe • vor 7 Tagen •via X (Twitter)

48 Kommentare

Profilbild von Edi Vilarinho
Edi Vilarinhovor 7 Tagen

Estressei o GPT-6.1 Sol Máximo ao limite no projeto Umbra hoje e os números do monitoramento são surreais. 🚀 Em apenas 191 requisições, o modelo processou um total de 27.9 MILHÕES de tokens. O grande destaque? 96% de taxa de acerto de cache no input (27.7M). Otimização absurda de contexto. 🧵👇 Mas o ritmo cobrou o preço: a intensidade de geração de código foi tão alta que torrei a cota de 5 horas em apenas 3h e 2min (ritmo de 33%/h). Foram 193.6K tokens de saída, com 49.5K dedicados só ao reasoning. O modelo voa, mas é preciso monitorar de perto para não ficar sem cota no meio do flow! 😅💻

Profilbild von shownotover
shownotovervor 7 Tagen

Yeah man, you got such a large amount of tokens only because the model is so slow. Look at how many tokens it processed in under 3 hours. Opus 5.5 would have processed 60 million tokens in 1 hour. It's not good being a Codex user now.

Profilbild von Edi Vilarinho
Edi Vilarinhovor 7 Tagen

Outro caso que eu testei 30/09 - 14:50 - sol 6.1 high 30/09 - 19:54 - sol 6.1 high 1.5x 01/10 - 00:54 - sol 6.1 high

Profilbild von Sahil Panhotra | Indie Builder
Sahil Panhotra | Indie Buildervor 7 Tagen

so jusy 36$ weekly in api usage 🫠

Profilbild von shownotover
shownotovervor 7 Tagen

kinda... First it was $360 / month... then $300 ... and now it has come to this

Profilbild von Sahil Panhotra | Indie Builder
Sahil Panhotra | Indie Buildervor 7 Tagen

🫠

Profilbild von shownotover
shownotovervor 7 Tagen

I used for FASTEST and CHEAPEST scarping service... they support MCP server so... Best for my research tbh

Profilbild von VulKan
VulKanvor 7 Tagen

that is a rough usage and what?!! 12tps..🫠

Profilbild von shownotover
shownotovervor 7 Tagen

yeah... its really really really slow

Profilbild von Shahzeb Naveed
Shahzeb Naveedvor 7 Tagen

codex is nerfed...

Profilbild von shownotover
shownotovervor 7 Tagen

yeah

Profilbild von orvian
orvianvor 7 Tagen

switching to claude asap

Profilbild von shownotover
shownotovervor 7 Tagen

I bought $100 max 1.5 days ago... absolutly amazing!

Profilbild von James Malsawm
James Malsawmvor 7 Tagen

Thank for the warning in advance. For me $20 on Claude is the best.

Profilbild von shownotover
shownotovervor 7 Tagen

Yeah man, I bought $100 Claude max too

Profilbild von Zekun
Zekunvor 7 Tagen

Bro is still using GPT models? Why not embrace Opus/Fable 😭 I tested the tok/s on Sol and Astra, and they’re painfully slow compared to Opus/Fable.

Profilbild von shownotover
shownotovervor 7 Tagen

I bought Claude Max $100 just 1.5 days ago bro

Profilbild von Zekun
Zekunvor 6 Tagen

Perfect timing 😭

Profilbild von LEO
LEOvor 6 Tagen

As much as I hate OpenAI/Anthropic, anyone who uses MAX or even HIGH to make a point is a dumbass. You're not CERN or NASA evaluating something deep. You're not even the Supreme Court or a tiny biotech lab. You're just a doritos eating hobo creating a meme. Use slow or stfu.

Profilbild von Kekius Pisimus
Kekius Pisimusvor 7 Tagen

Delete Codex

Profilbild von shownotover
shownotovervor 7 Tagen

I can't... I paid $20

Profilbild von Kekius Pisimus
Kekius Pisimusvor 7 Tagen

I know you're a big fan of Scam Altman 😂

Profilbild von Frank T. Mackie
Frank T. Mackievor 7 Tagen

If you want real usage than maybe you should upgrade to a real Codex plan and stop bitching

Profilbild von shownotover
shownotovervor 6 Tagen

Oh my... What a beautiful statement... Through my tests (all figures public) Claude $20 > Codex $100 right now

Profilbild von Peter
Petervor 6 Tagen

So using fast does not really worth it, right?

Profilbild von shownotover
shownotovervor 6 Tagen

no... not at all

Profilbild von Artem
Artemvor 6 Tagen

I've never use gpt-6.1 on max 😅

Profilbild von shownotover
shownotovervor 7 Tagen

This is crazy bro... I wanna cry too

Profilbild von CuriousDev
CuriousDevvor 7 Tagen

I guess they can't afford the compute cost now and offering cheap inference is not adding up

Profilbild von shownotover
shownotovervor 7 Tagen

They are making bad after bad decisions... I loved codex in the past... now... I don't know why they are doing all this

Profilbild von CuriousDev
CuriousDevvor 7 Tagen

Bro tbh codex earlier was also best because of the repeated resets, which they cant anyway sustain

Profilbild von vineeth
vineethvor 6 Tagen

Hey bro, Increase the work you can get done with those tokens by employing tools and skills like RTK, ponytail, caveman etc. This harness incorporates all of them and more- it increases the work you can get done with those 300 Million tokens by like 2x

Profilbild von shownotover
shownotovervor 6 Tagen

thanks, good point, I know cavemen, should test them all! 🙏🏻

Profilbild von vineeth
vineethvor 6 Tagen

Glad to know i helped

Profilbild von NVortex
NVortexvor 7 Tagen

Do you recommend I stick with the €20 Codex plan or switch to Claude at €20/month?

Profilbild von shownotover
shownotovervor 6 Tagen

Switch to Claude... wayyyy better (I have tested both, if you don't trust my word, check my profile)

Profilbild von NVortex
NVortexvor 6 Tagen

Thanks for your response! Are the limits the same, though? I’m asking because I rarely hit the limit with Codex.

Profilbild von Noah
Noahvor 7 Tagen

48% of the weekly limit in 53 minutes is brutal 😭

Profilbild von shownotover
shownotovervor 6 Tagen

it gets worse bro... trust me

Profilbild von زويد
زويدvor 6 Tagen

It’s a good thing that I’m using Hermes for easy shifting. Bye Bye Codex Welcome Back Claude

Profilbild von Anon🇨🇭
Anon🇨🇭vor 6 Tagen

engagement farming classic

Profilbild von CODIFY
CODIFYvor 6 Tagen

Thanks for sharing this!

Profilbild von King of Cups
King of Cupsvor 6 Tagen

My expectations has been completely different.

Profilbild von 𝓖𝓪𝓶𝓮 𝓴𝓝𝓲𝓰𝓱𝓽 𝓟𝓵𝓪𝔂𝓼
𝓖𝓪𝓶𝓮 𝓴𝓝𝓲𝓰𝓱𝓽 𝓟𝓵𝓪𝔂𝓼vor 6 Tagen

Using Luna on high is really good! Never hitting my 5hr limit anymore!

Profilbild von yocoo
yocoovor 6 Tagen

快速模式,周额度 48% 的量,居然有 3700 万token。那么普通模式周额度可以有 1.9 亿token。看起来还可以的样子

Profilbild von shownotover
shownotovervor 6 Tagen

Check Claude Pro $20 That gives you 2 BIllion tokens per month... 500 Million per week for Opus 5.5 (Top model in the world)

Profilbild von yocoo
yocoovor 6 Tagen

clsude的额度确实慷慨

Profilbild von P3xill
P3xillvor 6 Tagen

How do you remove the 5h limit?

Ähnliche Videos

I tested Claude Code on a fresh account - 1,500 lines of HTML cost me 50% of my window. Full video and summary is here.. I just ran a recorded test on Claude Code with a fresh account (Pro, not Max - my main account was 20x Max) , and the result is honestly insane. The task was trivial: create 3 simple demo HTML pages, around 500 lines each. Roughly 1,500 lines of code total. Nothing massive. Nothing enterprise-grade. Nothing that should meaningfully stress a premium coding product. And yet Claude Code burned through 40% of my 5-hour window almost immediately. I ran the exact same test with Codex, and it consumed only 2%. Then it got even worse: after the session ended, I did absolutely nothing for 15 minutes, and Claude still ate another 10%. Total: 50% of the 5-hour window gone for a tiny HTML demo. My weekly usage had already started at 2% before I even really used it, and after this tiny test it jumped to 8%. Now let us be generous and assume this entire run used around 30k tokens total. If 30k tokens represents 10% of weekly usage, that implies around 300k tokens per week. That is roughly 1.2M-1.3M tokens per month, and even if you round up aggressively, you are still in the 1.5M token range. Using the Sonnet 4.6 pricing you list: $3 per 1M input tokens $15 per 1M output tokens How exactly is this supposed to make sense for a paid coding product? Because from the user side, this no longer looks like "premium usage protection." It looks like a quota system that is either wildly inefficient, badly broken, or being accounted in a way users are not being told about. And that is before I even get to my main account: my $200 Max plan now dies in a single day. Just a few months ago, similar or heavier usage would last me about a week. So no, I do not buy the "maybe you just used it more" excuse anymore. Something is clearly broken in Claude Code. Either token accounting is broken, context handling is broken, background consumption is broken, or all three. Alex Albert is this really the experience you want users to pay for? Just watch the video. I tried to be very transparent and clear for your team! I was fan of Claude but just disappointed! And if you want, send me the detailed token accounting for this session and let us inspect it together publicly. Because from where I am standing, this is no longer a small pricing annoyance. It looks like something seriously wrong is happening, and users deserve a real explanation.

Hayrettin Tüzel

26,854 Aufrufe • vor 6 Monaten