Загрузка видео...

Не удалось загрузить видео

На главную

Opus 5, Max, Fast: Prompts: 8 Input (cache write): 1,181,215 Input (no cache): 227,275 Cache read: 70,291,242 Output: 302,449 Total tokens: 72,002,181 Cost (USD): $117.7400 Most of the money was spent on trying to get the body and the swing not to look insane. I had to link like...

154,705 просмотров • 3 месяцев назад •via X (Twitter)

Комментарии: 35

Фото профиля ThePrimeagen
ThePrimeagen3 месяцев назад

also i love that the ball gets relatively bigger to my body the further i hit the ball. Somehow that just makes me so happy

Фото профиля Michael🧙
Michael🧙3 месяцев назад

Woh, thats crazy. you know back in 2002 this game would have made $5,000,000,000,000 on steam and now you can make it for $117

Фото профиля Zachary Meyer
Zachary Meyer3 месяцев назад

wow dude 5 yrs ago this would have been worth $15m total at least and you did this for only $117???

Фото профиля Barutoi
Barutoi3 месяцев назад

Is this supposed to be good or bad? Looks like wasted time and money to me.

Фото профиля Rovshan
Rovshan3 месяцев назад

Just don't tell your wife on what you spent this $117

Фото профиля Jason
Jason3 месяцев назад

I just one shotted that shit with Gemini 3 flash preview for $0.02. Output Tokens: 5,729 Total Tokens: 19,589 Total Cost (USD): $0.021740

Фото профиля waterfowl
waterfowl3 месяцев назад

there's something sad about the fact people are spending 72 million tokens on what is essentially a crappy flash game from 2001

Фото профиля Levi
Levi3 месяцев назад

“Vibe coding” prompts? Or were you in the loop?

Фото профиля ThePrimeagen
ThePrimeagen3 месяцев назад

/loop

Фото профиля Nate Wilson
Nate Wilson3 месяцев назад

The future is here! We can finally make 2005 flash games again. Thank you AI overlords!

Фото профиля montano
montano3 месяцев назад

it’s so over

Фото профиля Steve Brownlie
Steve Brownlie3 месяцев назад

and yet this is what golf games looked like on donkey hardware 36 years before ai...

Фото профиля ink
ink3 месяцев назад

i can't overstate how bad this looks

Фото профиля Ahmad Awais
Ahmad Awais3 месяцев назад

@naymur_dev time to do this with open models using @CommandCodeAI :P

Фото профиля keccak
keccak3 месяцев назад

You know back in the day you could have made it for free over a period of months and no one would have cared. Now you spent 117 $ over a few hours and no one cares.

Фото профиля Michael Lulev
Michael Lulev3 месяцев назад

Try creating the same thing using Grok 4.5 high in Grok Build. Compare the time it takes and the cost.

Фото профиля Brandon Falk
Brandon Falk3 месяцев назад

Please god tell me you're making a golf game but with qwop controls for the golfers arms/legs/swing.

Фото профиля Aman Shaikh 🇮🇳
Aman Shaikh 🇮🇳3 месяцев назад

Wasted time and money I would prefer Opus 5 and Fable 5 for prototypes not for the final product Also geni 3 is good too

Фото профиля David
David3 месяцев назад

Its only me or is 117$ a lot of money?

Фото профиля Michael Swengel
Michael Swengel3 месяцев назад

And this seemed like a good use of money?

Фото профиля Chandraprakash Darji
Chandraprakash Darji3 месяцев назад

$117, is more than my infra bill. See this kind of ui/frontend/design with AI, I feel like AI is very far behind at building frontend.

Фото профиля troneras
troneras3 месяцев назад

Can I add your game as an Easter egg in my app website? It’s about golf. I would keep this like an art piece generated by @ThePrimeagen Now that anyone can build, like painting, we may get more people that admires good craftmanship…

Фото профиля Nat Miletic
Nat Miletic3 месяцев назад

It's these dumb things usually that eat up all of the tokens I swear LOL

Фото профиля Nicholas Gilmet
Nicholas Gilmet3 месяцев назад

Love all your stuff, Prime. No hate from me here; I default to agreeing with your takes on most things. Just wanna ask: is this you saying “look how good this model is!” Or “look how bad this model did here!” ? I can’t tell. I could just be dumb tho

Фото профиля Prasenjit Sarkar
Prasenjit Sarkar3 месяцев назад

Campfire ( ) generates a cost card per session: backend, model, token breakdown, USD total. Shareable with the team. Cost-cascade mode runs the same task across multiple backends in isolated worktrees, so you can see what each one actually costs before committing.

Фото профиля Mefa
Mefa3 месяцев назад

Lmfao what is this slop 😭

Фото профиля Mikhail Rogov
Mikhail Rogov3 месяцев назад

72M tokens for $118. Cache reads completely change what token count means.

Фото профиля Carlos
Carlos3 месяцев назад

this is where I am puzzled; I see this slop and I am like well those are similar results to what I get; but then I see in X some people claiming they one shot a Call of Duty with 3d?! someone must be lying 😛

Фото профиля relentless.build
relentless.build3 месяцев назад

People: "Look at this absurd golf thing I made for $117!" Also people: "$90 for GTA 6 is too expensive!"

Фото профиля intern
intern3 месяцев назад

$117? That’s wild

Фото профиля Tor Tor
Tor Tor3 месяцев назад

I have a 20 subscription Used cliproxyapi To serve my own agent Did a similar test run yesterday Total token cap set to 10m It works fine, not even trigger the 5h limit. API price is not for individuals...

Фото профиля Jorge
Jorge3 месяцев назад

I think at this point the best AI workflow pipeline is scaffold stuff → tweak a few things → ce-simplify-code → ask the AI to explain to you the codebase and get back to tweak a few things manually The smallest details you want changed live in a few easily identifiable files, it makes no sense to get an AI to take like 3 minutes for a 20 second surgical change you can Ctrl-F / rg

Фото профиля Tasa - 🇪🇸 🏴‍☠️
Tasa - 🇪🇸 🏴‍☠️3 месяцев назад

Yeah you'd need some skills you know.

Фото профиля Alexandru Bogdan
Alexandru Bogdan3 месяцев назад

Are you content with using this AI model?

Фото профиля Amadej Jerlah
Amadej Jerlah3 месяцев назад

hope there's room for 1 million ads

Похожие видео

How to cut your AI bill by 60% switching to Opus 5.5: Most people will swap the model name, save 24%, and stop there. The other 37% is sitting in your settings. Here's the real before and after on an example agent workload. One month: 100M input tokens (80M cached reads, 5M cache writes, 15M uncached) 10M output tokens BEFORE: Opus 5 Cache reads: 80M × $0.50 = $40 Cache writes: 5M × $6.25 = $31.25 Uncached input: 15M × $5 = $75 Output: 10M × $25 = $250 Total: $396.25 STEP 1. Just switch the model. Same tokens, new prices. Cache reads $0.20. Writes $5. Input $4. Output $20. $16 + $25 + $60 + $200 = $301 24% cheaper. That's what everyone's screenshotting. STEP 2. Let it write less. Box measured Opus 5.5 at 40% less verbose with no drop in accuracy. 10M output tokens becomes 6M. Output drops from $200 to $120. Total: $221. Now you're at 44% off. STEP 3. Stop running every call at max effort. Thinking can't be switched off on 5.5 anymore, so effort is your lever. Classifying, routing, formatting, summarizing? Drop the effort. Save the high settings for the calls that actually reason. Say that trims output another 25%, 6M down to 4.5M. Output: $90. Total: $191. 52% off. STEP 4. Cache the stuff you keep resending. This is the one nobody does. Cache reads went from $0.50 to $0.20. That's 60% off the cheapest line on your bill. Move your system prompt, tool definitions and repo context into the cache. Uncached input drops from 15M to 5M, cache reads go up to 90M. $18 + $25 + $20 + $90 = $153 AFTER: $153 From $396.25. 61% cheaper. Same work. The model gave you 24%. You gave yourself the other 37%. Anthropic's own number is 40% cheaper than Opus 5 on typical workloads. Your number depends on how much of your bill is output and how much of your prompt you're resending uncached every call. So check those two first. Bookmark this for when you migrate. follow CyrilXBT

CyrilXBT

15,803 просмотров • 1 месяц назад

Jev + Opus 5.5: Anthropic's new model beats GPT-6 Astra for 1/5 the cost, and 4 API changes will 400 your agent before it writes a single line I pulled these 10 steps from the migration docs so you don't learn them in production step 1 → $4 / $20 per 1M. Opus 5 was $5 / $25. cache reads dropped from $0.50 to $0.20 step 2 → 66.4% on Terminal-Bench 4.0 vs GPT-6 Astra 57.9% and Opus 5 52.3%. +14.1 points in one release, and on FrontierCode it beats Astra at default effort for 1/5 the cost step 3 → thinking can't be turned off anymore. send thinking: disabled and you get a 400. drop the field, set effort step 4 → tool_choice any and tool are gone. 400. switch to auto + strict step 5 → edit anything above a thinking block and the request dies. append only, or opt into drop_block step 6 → computer_20251124 is dead on the API. 400. move to computer_toolset_20260801 step 7 → the quiet one: default effort fell from high to medium. your agent thinks less than you set it up to and nothing tells you step 8 → hop Opus 5.5 → Sonnet 5 → Opus 5.5 and you pay 4.36 instead of 3.32. +31%, the cache dies and Sonnet can't read Opus's reasoning step 9 → change effort at the top of the request and the cache is gone. Jev sets it per message and the cache stays step 10 → switch fast - standard mid-session and it's a full cache miss. Jev picks speed once, on turn one one model, three knobs, zero 400s. that is Jev + Opus 5.5 send this to your Claude Code before you touch the model ID, then read my full Jev deep dive in the article below ↓

Carnage

16,674 просмотров • 1 месяц назад

Redis built a cache that cuts LLM costs by 90%! Production LLM apps do not receive completely new questions every time. A customer-support assistant might receive all three of these: - "Can I get a refund after buying the monthly plan?" - "Is the monthly subscription refundable?" - "Can I cancel the plan and get my money back?" The wording is different, but the underlying question and its answer remain the same. Yet LLM apps process every version as a new request. They assemble the prompt, send it to the model, and generate an answer that may have already been generated. Prefix caching reduces part of these repeated calls. When requests begin with the same system prompt or context, the model can reuse the KV states already computed for that shared prefix. But the request still hits the LLM. The new tokens must be processed, and the complete answer must still be decoded. So even with a prefix-cache hit, there's another generation call involved. To solve this, instead of only caching computation inside the model, the application can cache the generated response outside it. When another question arrives, the system embeds it and compares it with previously answered questions. If it finds a sufficiently close match, it returns the stored response without invoking the LLM again. A cache hit removes the input tokens, output tokens, and decoding time associated with another LLM call. In practice, it is important to decide which questions can safely share an answer since a production setup needs well-tuned similarity thresholds, expiration policies, data isolation, and monitoring for incorrect matches. If you want to use this in practice, Redis already implements it as a managed service called Redis LangCache. Under the hood, it generates embeddings, searches previous responses, and returns a matching answer before another model call occurs. Redis also handles access scopes, custom filtering, TTL and eviction controls, and cache monitoring through Redis Cloud. I built an interface to compare it against direct LLM inference. The video below shows this in action, and I worked with Redis on this post to put this together. For the paraphrased question in my run, direct inference took 2.232 seconds and consumed 514 input tokens plus 250 output tokens. Redis returned the earlier response in 0.37 seconds with zero LLM input or output tokens. That was roughly 6x faster in this run. Redis reports API cost savings of up to 90% and cache-hit responses up to 15x faster. The actual result depends on how much safe repetition exists in the workload. You can try Redis LangCache here: If you want to dive deeper, I have already written a detailed breakdown of KV, prefix, prompt, and semantic caching in the article quoted below. This demo builds on the final technique and shows it running in practice. Read it below.

Avi Chawla

166,230 просмотров • 1 месяц назад