gpt-5.4-mini

gpt-5.4-mini

GPT‑5.4‑mini is a compact, cost‑efficient model designed for reliable performance across high‑volume, everyday AI workloads.
Azure OpenAI
Direct from Azure
Version: 2026-03-17

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.
  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.
  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.
  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models .

About this model

GPT‑5.4‑mini is a compact, cost‑efficient model designed for reliable performance across high‑volume, everyday AI workloads.

Key model capabilities

  • Most capable OpenAI frontier model for professional work
  • Stronger reasoning for complex, multi‑step tasks
  • Built‑in agentic workflows for planning and execution
  • Native computer use (keyboard, mouse, screenshots)
  • Tool Search for efficient large tool ecosystems
  • Supports very large context for long documents and workflows
  • Improved token efficiency for faster, lower‑cost responses
  • Enhanced coding and software automation reliability
  • Higher factual accuracy and reduced hallucinations

Key use cases

GPT‑5.4-mini is built for professional knowledge work, including document and spreadsheet creation, coding, data analysis, agentic workflows, and software automation.

Out of scope use cases

The provider has not supplied this information.

Quick facts

Model providerAzure OpenAI
TypeChat completion, Responses
LifecycleGenerally available (GA)
Input typetext, image
Output typetext
Context window400k
Token limits128k output

Related models