· Updated
/fast mode — a speed setting that runs GPT-5.4 at 1.5x normal speed with the same intelligence and reasoning. Credits are consumed at 2x the standard rate when fast mode is active. It works across Codex IDE Extensions, Codex CLI, and the Codex app when signed in with ChatGPT.Speed without an intelligence tradeoff changes how developers approach iteration cycles. When debugging a hard bug or rapidly testing changes, waiting on each response breaks concentration — faster output keeps the cognitive loop intact and reduces context switching between thinking and acting.
Type /fast in Codex to activate. It's available in the IDE extension, CLI, and the Codex app — note that API key sessions use standard pricing and don't support /fast. A separate GPT-5.3-Codex-Spark model also exists — a less-capable option optimized for near-instant iteration, in research preview for ChatGPT Pro subscribers.
Codex got more speed. With /fast mode, GPT-5.4 runs 1.5x faster with the same intelligence and reasoning. Move through coding tasks, iteration, and debugging while staying in flow. https://t.co/Xlzmeozzc4
More like this
OpenAIFeb 5
WindsurfMar 20
Anthropic15h ago
OpenRouter5d ago