User drains Codex quota in hours using only Luna Max
Al_Grigor · x · 2026-08-20
A user attempted to save Codex credits by exclusively using the Luna Max model, only to drain the entire quota in just a few hours. This sparked complaints about the high consumption rate of specific models.
More from Models
- Cohere study finds 14B models outperform larger ones in linguistic reasoning challenge — Cohere_Labs · 2026-08-20
- Train a 135M parameter LM in 2.5 hours: A full journey — EAccelerate_42 · 2026-08-20
- Ornith-1.5-9B trends on Hugging Face with image-text-to-text support — ornith-ai · 2026-08-20
- Refusal-removed Qwen2.5-72B runs on Mac, zero refusals with high risks — petrusenko_max · 2026-08-20
- Tencent Prepares Larger Multimodal Model Hy4 for Release — zephyr_z9 · 2026-08-20
- Aurora-80K releases: A modern tiny LLM with 80K params — Tall_Abrocoma_3533 · 2026-08-20