Model Releases
These optimizations across our stack compound to unlock the most performant models at every point in the cost-intelligence curve. https://op…
OpenAI announced the release of GPT‑5.6 Sol after deployment, incorporating optimizations across its stack to enhance run‑time efficiency. The update delivers a roughly 20 % reduction in serving costs
OpenAI announced the release of GPT‑5.6 Sol after deployment, incorporating optimizations across its stack to enhance run‑time efficiency. The update delivers a roughly 20 % reduction in serving costs through improved production GPU kernels and more than 15 % higher token‑generation efficiency via advanced speculative decoding. These gains demonstrate the model’s increased performance at every point on the cost‑intelligence curve.
Source: OpenAI (X) | 2026-07-29