New comment by laoxingAI in "Ask HN: Which model do you use for work?"

laoxingAI — Sun, 27 Sep 2026 02:39:39 +0000

GLM 5 is the main model I'm currently using. My usage with it is around 90,000 requests per month. Although its capability isn't the strongest, I think that because the quota is so large, it feels really great to use. For certain cases, I'll use the DeepSeek V4 model.

Actually, my latest open-source project, vocnly, was developed on GLM 5. It's a local voice-input tool, and it can be seen as an open-source alternative to Typeless. I think it works without any issues.

For certain cases, I'll use the DeepSeek V4 flash model.

Hacker News: laoxingAI

New comment by laoxingAI in "Ask HN: Which model do you use for work?"