DeepSeek's new model shows abnormal cache write costs, beating GPT without them
teortaxesTex · x · 2026-07-31
A developer reported that the API cost for DeepSeek's new model (suspected v4 flash 0731) in Artificial Analysis benchmarks shows an abnormally high 'cache write fee'.
If this unexplained cache creation cost is excluded, the model's performance-to-cost Pareto frontier would outperform GPT 5.6 luna.
Related event: DeepSeek V4-Flash: Agent Leap, Open Source, Ultra-Low Price(100 posts)→
More from Models
- Users report Gemini's memories can't actually be deleted even after wiping chat history — ThrowRA_Purpose2025 · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
- Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16