Loading
Loading
Comments
Hacker News published a model update. If you use a hosted chat, read the source before you assume your usual model changed.
GLM 5.3 Flash is on the cloud board. List cost is $0.15 in and $0.5 out per million tokens. GLM 5.3 Flash needs about 80 GB for the weights (EXL3, per Mia).
Try GLM 5.3 Flash. Copy the OpenRouter call.
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"z-ai/glm-5.3-flash","messages":[{"role":"user","content":"Hello"}]}'Published 2026-10-02T15:29:15.000Z. FitStack shortens the story so you can decide. The source owns the detail.