More posts
I upgraded to Google's top AI tier and I'm not mad about it. Two prices: $99.99 for 5x usage, $199.99 for 20x. Both come with monthly Cloud credits, $40 or $100, which you can burn on Gemini API calls. The $300 credit for new accounts is one and done, but Ultra's keep arriving, and they cover third party models too, Claude, Grok, DeepSeek, Kimi. Twelve months of that and the plan costs about half what you're paying. The Gemini app has 4 Argon plus Gemini Spark, an agent that just stays on between your messages. Flow hands you 10,000 to 25,000 credits, enough video generation that I stopped counting. Flow Music is 30,000 credits a month, around 6,000 songs, commercial use included. Antigravity runs 4 Argon and the weekly quota doesn't bottleneck me. Only thing I hate is the 5 hour refresh window. Standard Google stuff comes with it too: 20 to 30 TB of storage, YouTube Premium, Home Premium Advanced, an AI coach in Google Health.
Here's the insane part: Google puts "training data" and "chat history" behind one toggle called "Keep Activity." Leave it on and you feed the model by default, paid users and all. Turn it off and you're out of training, but you also lose your chat memory and linked apps. For anything sensitive, stick to Temporary Chat.
You talk out loud with Lily, live. She answers, and she asks follow-ups, so it lands closer to a real conversation than to a lesson. That's the part that makes it useful for speaking. • New Super accounts get unlimited calls already. Anyone on Super before today gets them before the year is out. • Duolingo stops selling Max this month. Individual Max users get switched to Super Family at the price they pay now. • Cost per call went from $0.30 to under $0.01, mostly because they moved to open-source models. Six languages for now: English, French, Spanish, Italian, German, Portuguese.
. It's their open-source flagship, and somehow it's stronger, steadier, and cheaper than the preview at the same time. It can see now. First one with vision: charts, math, fine-grained images, it reads them without tripping up. It also knows how to drive a computer. Blender, CAD, GUI or CLI, it works them directly. Pricing, per million tokens: - Input ~$0.90 - Output ~$2.70 - Cached input ~$0.045 A cheaper HY4 Flash is coming too. Freebies for now: - Nov 4–15: WorkBuddy and CodeBuddy are free - Tencent Cloud TokenHub half off through Dec 31, 2026
