Tested Qwen 3.8 flash for our beloved pelican.
The results look good but it was slowwwww af It took around an hour for this. I think I'll stick to DeepSeek V4.1 flash ✌︎㋡
Deepseek 4.1 nvidia dgx spark opensource freedom.
1 HTML file multiple levels
The $200 tier just got folded 💀
Same one-shot 3D prompt. 4 cheaper models. No premium frontier model needed. DeepSeek → fastest HY4 → weirdest, but surprisingly good Gemini → most feature-packed Muse Spark → the real surprise And here’s the uncomfortable part: NONE OF
This is getting crazy. Just look at what deepseek v4.1 flash cooked in literally 2 minutes for absolutely FREE
Gave it the same viral one-shot pirate ship prompt it did an amazing job. didn’t even touch an agentic harness either, generated this straight in the vanilla web UI
You have reached the end of the archive
All of deepseek