Codex Gets a /fast Mode for 1.5x Faster Coding

OpenAI

Mar 5, 2026 · Updated Apr 26, 2026

Codex now supports /fast mode, running GPT-5.4 at 1.5x speed with no drop in intelligence or reasoning. Credits are consumed at double the standard rate — the speed-cost tradeoff for developers who want to stay in flow.

Codex, OpenAI's coding agent, added /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.

View the full update on developers.openai.com

OpenAI Developers

@OpenAIDevsMar 5

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

175

View on X

Every HeadsUpAI update is written based on its original source and reviewed before it's published. Read our editorial standards →

See all AI news & updates from OpenAI →

Keep reading

GPT-5.3-Codex Unifies Coding and Reasoning With Near-Double Computer-Use Accuracy

OpenAI released GPT-5.3-Codex, merging GPT-5.2-Codex's frontier coding performance with GPT-5.2's reasoning and professional knowledge into a single model that's 25% faster. It sets new state-of-the-art scores on SWE-Bench Pro and Terminal-Bench while nearly doubling computer-use accuracy on OSWorld-Verified to 64.7%.

Windsurf Adds GPT-5.4 Mini for Faster Coding and Subagent Workflows

WindsurfMar 20

Windsurf Adds GPT-5.4 Mini for Faster Coding and Subagent Workflows

Windsurf now supports GPT-5.4 mini, OpenAI's model optimized for coding, computer use, multimodal understanding, and subagents. It runs 2x faster than GPT-5 mini, making it a quicker option for developers already working inside the IDE.

AnthropicMay 18

Anthropic Makes Opus 4.7 the Default for Claude Code Fast Mode

Anthropic updated Claude Code to use Opus 4.7 as the default model for its high-speed Fast mode configuration. The update delivers identical reasoning quality at 2.5x the response speed by prioritizing low latency over cost efficiency for interactive developer workflows.

OpenRouter Launches Claude Opus 4.7 Fast Mode for High Speed Reasoning

OpenRouterMay 13

OpenRouter Launches Claude Opus 4.7 Fast Mode for High Speed Reasoning

OpenRouter enabled a high-speed inference tier for Anthropic's flagship model, delivering 2.5x faster throughput at a 6x price premium. This update allows developers to trade capital for speed in latency-sensitive agentic workflows without sacrificing reasoning depth.