
Tony
@EnvolDev • 3,218 subscribers
Racing top AI models: same prompt, real cost & time Building SaaS apps & tools with AI First on everything new, and only what matters https://t.co/b3B64125mb & https://t.co/rr4w8RX7eJ
Shorts
Videos

GPT-6.2 Astra vs Fable 5.2 🧊 GPT-6.2 Astra is almost 10x cheaper and almost 3x faster than Fable 5.2. 🤯 But the quality is nowhere near Fable 5.2. 😬 Mixed feelings. Same Cathedral of Ice prompt: Fable 5.2: $81.10 · 1h 56m 52s GPT-6.2 Astra: $8.20 · 40m 34s For coding and debugging, GPT-6.2 Astra is going to be a game changer. For UI design and visuals, Fable 5.2 is still far ahead. Cheap and fast, or the best quality? 👀
Tony138,899 просмотров • 9 часов назад

GPT-6.2 Astra vs GPT-6.2 Sol vs Fable 5.2 vs Opus 5.5 🛩️ GPT-6.2 Astra is just f*cking insane. 🤯 OpenAI is so f*cking back. Over 21x cheaper and almost 4x faster than Fable 5.2. And the detail on this plane is unreal. 😱 Same Alpine Gold prompt: GPT-6.2 Astra: $9.62 · 46m 14s GPT-6.2 Sol: $2.07 · 30m 47s Fable 5.2: $209.50 · 3h 02m 54s Opus 5.5: $31.85 · 2h 45m 42s And GPT-6.2 Sol did it for $2.07. Over 100x cheaper than Fable 5.2. 💀 Is Anthropic in trouble? 👀
Tony78,169 просмотров • 7 часов назад

Claude Fable 5.2 vs Claude Opus 5.5 🧊 The first Fable 5.2 result is here. And it's totally insane. 🤯 Same prompt. Cathedral of Ice. Fable 5.2: $81.10 · 1h 56m 52s Opus 5.5: $45.97 · 3h 11m 26s I know I say it every time, but this is a huge leap. A huge jump. 😱 Fable cost more, but it finished 1h 15m faster. And just look at the ice, the ship, the whale. 👀 The future looks bright and amazing. 🔥 What do you guys think?
Tony388,398 просмотров • 8 дней назад

Fable 5.2 vs Gemini 4 Hydrogen vs Opus 5.5 vs GPT-6 Astra ☁️ Gemini 4 Hydrogen made the whole film for $6.21. 🤯 But it's the least good of all. 😬 Same prompt: Rio Above the Clouds Opus 5.5: $60.89 · 2h 19m 35s Fable 5.2: $76.04 · 1h 59m 11s Gemini 4 Hydrogen: $6.21 · 1h 33m 48s GPT-6 Astra: $16.89 · 34m 06s And this time it ran on Extra High. In my last test, it could only run on High. So no excuses. I know I can't compare it to frontier models like Fable 5.2 or Opus 5.5. But the result was not good at all. GPT-6 Astra cost only $10.68 more, finished almost 1 hour faster, and made a better film. I'm not impressed at all by Hydrogen on this one. 🤦 What do you guys think? 👀
Tony134,752 просмотров • 3 дней назад

Claude Opus 5.5 High vs Extra High vs Max vs Ultra 🧊 Everyone's been wondering: does effort really matter? Same model. Same prompt. Only the setting changes. High: $26.01 · 2h 17m 21s Extra High: $45.97 · 3h 11m 26s Max: $84.93 · 3h 37m 47s Ultra: $681.91 · 10h 47m 40s Ultra cost $681.91 for a 25-second film. 🤯 That's 26x High... and 8x Max. 😱 For me, Extra High is the sweet spot: quality, time and money. That's why I always pick it. So, does effort really matter? Which one would you pick? 👀
Tony294,639 просмотров • 11 дней назад

Claude Fable 5.2 Medium vs High vs Extra High vs Max 🛩️ Does effort really matter? Now it's Fable 5.2's turn. Same model. Same prompt. Only the setting changes. Medium: $61.90 · 1h 49m 39s High: $77.90 · 1h 48m 45s Extra High: $209.50 · 3h 02m 54s Max: $288.25 · 3h 19m 53s Max cost $288.25 for a 25-second film. 🤯 That's 4.7x Medium... and 3.7x High. 😱 But Max is the best of all. Hands down. It took only 17 minutes more than Extra High. Yes, it costs more, but the difference is huge. So, does effort really matter? Which one would you pick? 👀
Tony77,607 просмотров • 4 дней назад

Gemini 4 Hydrogen vs Gemini 4 Carbon 🧊 Gemini 4 Hydrogen is out 😱 I'm very surprised by how fast and cheap it is. I'm very impressed by it. Almost twice as fast and half the price of Gemini 4 Carbon. Gemini 4 Hydrogen: $4.27 · 1h 23m 40s Gemini 4 Carbon: $8.83 · 2h 39m 10s Both ran on High.OpenRouter only let me use High. On Extra High, it must be even better. What do you guys think? 👀
Tony56,261 просмотров • 5 дней назад

Gemini 4 Argon vs Sonnet 5.5 vs GPT-6 Astra vs Opus 5.5 Honestly, Gemini 4 Argon blew me away. 🤯 It's 4x cheaper than Opus and 7x faster, and it still looks incredible. Opus is still the king, obviously, at that price and time. But I'm really liking Gemini on this one. What do you guys think? 👀
Tony215,918 просмотров • 1 месяц назад

Claude Opus 5.5 vs GPT-6.1 Sol vs GPT-6 Astra vs GPT-6.1 Terra 🧊 Same prompt, four models: Claude Opus 5.5: $45.97 · 3h 11m 26s GPT-6.1 Sol: $3.11 · 54m 19s GPT-6 Astra: $17.51 · 1h 00m 22s GPT-6.1 Terra: $1.49 · 59m 28s Obviously, Opus is way ahead. 🤯 But it cost 30x more than Terra. 😱
Tony103,918 просмотров • 17 дней назад

🚨 Opus 5.5: Today vs. At Launch — Nerfed? 👀 With everyone talking about a possible nerf, I had to test it myself! I reran the Eiffel Tower benchmark, and honestly, I prefer the launch result. It honestly feels like Opus 5.5 got little nerfed. The tower itself might have slightly better detail now, but the surrounding buildings, trees, river, and overall scene look noticeably worse to me. One run doesn’t prove a nerf, but this comparison surprised me. I want to see whether the same pattern shows up in the night train benchmark next! 🚂🌙 What do you think: nerf or normal variation? 🤔
Tony264,601 просмотров • 1 месяц назад

GPT-6 Astra High vs Extra High vs Max vs Ultra 🏔️ Everyone's been wondering: does effort really matter? Same model. Same prompt. Only the effort changes. High: $8.99 · 21m 25s Extra High: $17.82 · 51m 10s Max: $23.60 · 1h 27m 10s Ultra: $59.75 · 1h 01m 17s High → Extra High is a huge jump. 🤯 Ultra costs 6.6x more than High... and still finished faster than Max. 😱 So, does effort really matter? Which one wins for you? 👀
Tony60,181 просмотров • 14 дней назад

Gemini 4 Argon vs Opus 5.5Benchmark is in: The Space Train 🚂🪐 4 minutes. $3.40. That's all Gemini needed 🤯 Same prompt: Opus took 1h 53m and cost $23.46. Gemini took 4m 20s and cost $3.40. That's 26x faster and 7x cheaper 😱 Did it beat Opus? No. Opus is still ahead on detail: the volumetric clouds, the mechanics on the locomotive, the camera work. But the gap is way smaller than the price gap. Gemini still pulled off the station, the planets and the lightning, in less time than it takes to make a coffee ☕ When you need something good in minutes, not perfect in 2 hours, this is nuts. Watch them side by side and tell me: is Opus worth 7x the price here? 👀
Tony100,934 просмотров • 1 месяц назад

DeepSeek V4.1 Flash 1017 just embarrassed everyone. 🤯 Same prompt: a working four-stroke engine cutaway. DeepSeek V4.1 Flash 1017: $0.36 · 1h 54m 16s Claude Opus 5.5: $21.81 · 2h 00m 13s GPT-6.1 Terra: $0.43 · 9m 09s GPT-6 Astra: $7.33 · 54m 33s Opus got it right. No surprise there. But DeepSeek? As good as Claude, maybe the most beautiful one of the four… for 36 cents. That's 60x cheaper than Opus. This is nuts. Yes, Terra is fast. But costing more than DeepSeek? That's a joke. 😂 Which one wins for you? 👇
Tony51,401 просмотров • 18 дней назад

Claude Sonnet 5.5 vs GPT-6.1 Terra vs DeepSeek V4.1 Flash 1017 vs GPT-6.1 Sol 🚀 Sol is incredible on this one. 🤯 Terra: 89x cheaper than Sonnet and almost 9x faster. 😱 Same prompt - One shot Sonnet: $67.73 · 3h 05m 56s Terra: $0.76 · 21m 19s DeepSeek V4.1 Flash 1017: $0.39 · 1h 18m 10s Sol: $2.05 · 42m 46s Which one wins for you? 👀
Tony33,126 просмотров • 12 дней назад

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.
Tony112,633 просмотров • 1 месяц назад

🚨 Opus 5.5 Night Train: Today vs. At Launch, and this one is worse 👀 As promised, I reran the night train benchmark. Same prompt as at launch. Same pattern as the Eiffel Tower, and to me it's even more visible. But again: small details up, overall scene down. Two benchmarks. Same direction. Am I wrong, or do you see it too? 👇
Tony70,541 просмотров • 1 месяц назад

DeepSeek V4.1 Flash 1017 vs GPT-6 Astra The Space Train 🚂🪐 Am I crazy or did DeepSeek just beat Astra on this Space Train benchmark??? 😱 Astra took 40m 18s and cost $14.37. DeepSeek took 2h 07m and cost $0.40. That's 36x cheaper. Forty cents!! 🤯 DeepSeek V4.1 Flash 1017. Remember that name. Watch them side by side and tell me: is Astra worth 36x the price here? 👀 Google Gemini Google OpenAI ChatGPT
Tony49,604 просмотров • 1 месяц назад