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

Windsurf

Mar 20, 2026 · Updated Apr 25, 2026

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.

Windsurf, an AI-native IDE built by Codeium, now includes GPT-5.4 mini as an available model. According to OpenAI, the model is optimized for coding, computer use, multimodal understanding, and subagent workflows — covering the core capabilities developers rely on in agentic coding sessions. It runs 2x faster than GPT-5 mini, making it a lower-latency option for agentic tasks inside the editor.

For developers already using Windsurf's agentic features, the 2x speed gain directly reduces wait times across multi-step workflows. OpenAI's subagent optimization aligns with how coding agents work in practice — generating code, running tests, and iterating across files in a single session, where each step involves a model call.

GPT-5.4 mini is available now in Windsurf's model selector. It's worth testing on longer agentic sessions where latency compounds across multiple sequential model calls.

View the full update on windsurf.com

Windsurf

@windsurfMar 17

GPT-5.4 mini is now available in Windsurf!

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 Cognition →

Keep reading

Windsurf Integrates GPT-5.5 to Power Parallel Agentic Coding Workflows

Windsurf added OpenAI's new GPT-5.5 model to its AI-native editor to improve how agents handle complex, multi-step engineering tasks. The update focuses on reducing human intervention by better interpreting ambiguous instructions and managing long-horizon goals.

OpenAI Launches GPT-5.4 Mini and Nano for Fast, Low-Cost Agentic Workflows

OpenAIMar 19

OpenAI Launches GPT-5.4 Mini and Nano for Fast, Low-Cost Agentic Workflows

OpenAI released GPT-5.4 mini and nano, its most capable small models yet. Mini runs more than 2x faster than GPT-5 mini with strong coding, tool use, and computer-use scores. Nano is the smallest, cheapest option, built for high-volume simple tasks.

OpenRouter Adds GPT-5.4 Mini and Nano, Optimized for Agent Pipelines

OpenRouterMar 19

OpenRouter Adds GPT-5.4 Mini and Nano, Optimized for Agent Pipelines

OpenRouter adds GPT-5.4 mini and nano to its model catalog. Mini brings GPT-5.4-level capabilities at lower latency, while nano targets high-volume, cost-critical pipelines — both with 400K context and image input support.

Cognition Releases SWE-1.6 with Optimized Agent UX and Unmatched Speed

CognitionApr 9

Cognition Releases SWE-1.6 with Optimized Agent UX and Unmatched Speed

Cognition launched SWE-1.6 in the Windsurf IDE, a model post-trained to eliminate agentic friction like looping and overthinking. It delivers up to 950 tokens per second, prioritizing efficient multi-step trajectories over raw benchmark gains.