OpenAI Cuts Model Price by 80% via Kernel Optimization

OpenAI reduced the price of its GPT 5.6 Luna model by 80%, driving AI data analysis costs below half a cent. This massive price drop was enabled by using Codex to rewrite Triton kernels, reducing end-to-end serving costs by 20%.

2026-08-07 ~ 2026-08-07 · 2 related posts

• GPT-5.6 Rewrites Triton Kernels to Cut Serving Costs by 20%, Funding Luna Price Drop — JeremyCMorgan · 2026-08-07
• GPT 5.6 Luna Price Cut by 80%, AI Analytics Cost Drops Under Half a Cent — JeremyCMorgan · 2026-08-07