Thanks to everyone who joined yesterday's workshop with @AEDIA2024 and @dantart 🙌
Key takeaway: the spec is the source of truth. Let the agent iterate as much as it needs. ⚡
More sessions coming soon 👀
llmax.ai
Starting in 1 hour ⏰
Spec Driven Development + Unlimited Tokens with @AEDIA2024, @dantart & @mhergon.
5:00 PM CEST · live · 🇪🇸 in Spanish
👉 webinarllmaxai.aedia.es/
llmax.ai retweeted
Today at 5:00 PM CEST 🚀
Spec Driven Development + Unlimited Tokens, live with @AEDIA2024, @dantart & @mhergon.
Bring your agent, your specs and your questions.
🇪🇸 in Spanish
👉 webinarllmaxai.aedia.es/
#AIAgents
Today at 5:00 PM CEST 🚀
Spec Driven Development + Unlimited Tokens, live with @AEDIA2024, @dantart & @mhergon.
Bring your agent, your specs and your questions.
🇪🇸 in Spanish
👉 webinarllmaxai.aedia.es/
#AIAgents
Spec Driven Development in 4 steps 📝
1️⃣ Write the spec
2️⃣ Let the agent plan from it
3️⃣ Break it into tasks
4️⃣ Implement and verify against the spec
Token-heavy by design. Perfect for unlimited inference ⚡
Live tomorrow with @AEDIA2024 @dantart
👉 webinarllmaxai.aedia.es/
This Thursday 🔴
Spec Driven Development + Unlimited Tokens, live with @AEDIA2024, @dantart & @mhergon.
Let your agent iterate as much as it needs. No token counter.
🗓️ Thu, Oct 22 · 5:00 PM CEST · 🇪🇸 in Spanish
👉 webinarllmaxai.aedia.es/
#AIAgents
llmax.ai retweeted
AI inference for developers, with unlimited tokens for a fixed monthly price ⚡
→ Zero logs
→ GPUs in the EU 🇪🇺
→ Let your agents iterate without doing token math
👉 llmax.ai
AI inference for developers, with unlimited tokens for a fixed monthly price ⚡
→ Zero logs
→ GPUs in the EU 🇪🇺
→ Let your agents iterate without doing token math
👉 llmax.ai
Tokens shouldn't be the bottleneck for your AI agents. ⚡
Live workshop next week with @AEDIA2024: Spec Driven Development + Unlimited Tokens 🚀
With @dantart, @mhergon, Abraham Bravo
🗓️ Thu, Oct 22 · 5:00 PM CEST · 🇪🇸 in Spanish
webinarllmaxai.aedia.es/
#AIAgents #SpecDriven
Today at 12:00 CEST: how to stop paying your AI per word.
Open models, EU infrastructure, fixed capacity + a live cost case study. 60 min, free, in Spanish.
Last seats → luma.com/vyydrt9t
Two changes on llmax.ai today:
Smart is new. Pro is live.
Still flat rate. Still unlimited tokens. Still EU-only. 🇪🇺
What's the same on every plan:
unlimited tokens, unlimited requests (we limit RPM + concurrency, never tokens), model upgrades included, zero logs, EU infra, OpenAI-compatible API.
llmax.ai
Not sure flat rate is actually cheaper for your team?
We run the numbers live next Wednesday with @dantart & @startupsSI
12:00 CEST · free · in Spanish
luma.com/vyydrt9t
One week until we do AI pricing math live, in public, with a calculator. 🧮
Per-token vs flat rate. Same workload. May the cheapest model win.
Sept 23 · 12:00 CEST · Free · in Spanish luma.com/vyydrt9t
Pay-per-token is fine for a chatbot you poke twice a day.
It breaks when AI works like an employee: in the background, all day, on everything.
Nobody pays their engineers per word. (Imagine the Slack bill.)
Sept 23 webinar with @mhergon, @dantart & @startupsSI: → why per-use pricing breaks → open models, EU infra, fixed capacity → live case study: cost, predictability, quality, sovereignty
Free · 12:00 CEST · 🇪🇸 in Spanish luma.com/vyydrt9t
llmax.ai retweeted
Ya estamos online! Es uno de mis proyectos más personales, así que si quieres poder quemar tokens sin limites llmax.ai es para ti!
#ai #inference #unlimited