Crouton Alpha used 6.72M tokens on these 3 Three.js scenes.
This is a dev post classified by AGK Intelligence as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Crouton Alpha used 6.72M tokens on these 3 Three.js scenes. I ran the stealth model in OMP through OpenRouter. A lighthouse, a planet at war and a floating observatory. I kept asking for revisions. We also fixed a water shader before recording. 6,644,418 input tokens 75,591 output tokens 0 cached tokens reported Input includes context sent again on each call. I tried to identify the model by comparing token counts. 20 comparison models, 9 local tokenizers. No exact match. Pretty weak at Three.js in my tests. That does not tell me how it performs on other tasks. I am still curious who mad
Posted by Alexey Fateev (9.7k followers) 1 h ago · 2 likes · 349 views · view the original post on X. Kept by the Dev Radar as AI dev tools.
More dev work like this
- Your coding agent changed the code. What did it actually do? — @DanKornas
- Meituan Longcat 2.5 — @Chris_Wozniczek
- I tested Crouton Alpha via api and the results are weird and interesting. — @ItsmeAjayKV
- it's kimi day 👀 — @fanofaliens
- 厉害!一年不到,姚顺雨从空降到把混元Hy4推到开源第一梯队! — @NFT_Chen
- Hy4 is here ! — @ItsmeAjayKV
- three things your Hermes Agent picked up in v0.22.6: — @witcheer
- Mistral Large 4 (1T, open weights released 29 October) decodes at 23.7 tok/s on one Mac… — @niklaslenz_ai
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.4k posts from 5k X accounts over the last 21 days, 9.2k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-04 10:37 UTC. Full method.