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 Benchmarks Impress but Face Pricing Controversy(4 posts)→

Original post →

More from Models

Models channel →