@Marni Melrose Exactly, and it’s also a great out-of-the-box workspace interface where you can build almost anything using community plugins!

This is actually a bigger deal than it looks. For the first time, it feels like these models can reliably handle something as basic (and historically broken) as generating an alphabet in a true one-shot — without drifting, skipping, or hallucinating structure halfway through. If this holds, it’s not just about “better images” — it’s about finally trusting structured output in visual generation.

@Doug Keim Thanks for the feedback — really appreciate it 🙌Good to know this is actually useful. Regarding Gemini — honestly, even OpenClaw has already removed mentions from the docs about using Google paid subscriptions, because the ban risk is pretty high. I didn’t want to push anything that could put people’s accounts at risk — especially since most people have way more than just Gemini/Antigravity tied to their Google accounts (email, etc.). So I decided not to publish anything about that for now. As for OpenRouter and free models — I actually have a draft almost ready. I basically took all the free tiers, sorted them by strength, and set up a fallback chain so that once a stronger model hits its limit, it drops to the next one. So it always tries the strongest model first, then falls back if needed — and on every new request it starts from the top again (in case limits reset). I’ll try to push it to the classroom in the next few days 👍

https://www.skool.com/ai-agents-openclaw/classroom/513b4ce7?md=09cb8315e3254aedb6f90ecc092042bd it is here :)