← Models

GPT-5.4 mini

OpenAI · GPT-5

OpenAI's strongest mini model for coding, computer use, and fast high-volume agent workloads.

Part of GPT family · Other versions: GPT-5.5 Pro , GPT-5.5 , GPT-Rosalind , GPT-5.4 nano , GPT-5.4-Pro , GPT-5.4 , GPT-5.3 , GPT-5.3-Codex , GPT-5.2-Codex , GPT-5.2-Pro , GPT-5.2 , GPT-5-Codex , GPT-5 mini , GPT-5 , GPT-5 nano , GPT-4.1 , GPT-4o mini Transcribe , GPT-4o mini TTS , GPT-4o Transcribe , GPT-4o mini , GPT-4o
Type
language
Context
400K tokens
Max Output
128K tokens
Status
current
Input
$0.75/1M tok
Output
$4.5/1M tok
API Access
Yes
License
proprietary
coding computer-use subagents tool-use multimodal high-volume
Released March 2026 · Updated April 4, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on April 4, 2026.

GPT-5.4 mini is OpenAI’s newest mini-tier GPT model, released on March 17, 2026 as a faster, more capable successor to GPT-5 mini. OpenAI positions it as the small-model default when teams need better coding, tool use, and computer-use performance without paying flagship-model prices.

Capabilities

GPT-5.4 mini is strongest in coding assistants, subagent systems, screenshot-heavy computer-use flows, and high-volume tool-using workloads where latency directly affects product quality. OpenAI’s launch benchmarks also show it narrowing the gap with full GPT-5.4 on coding and OS-style interaction tasks more than earlier mini tiers did.

Technical Details

OpenAI’s current model docs list GPT-5.4 mini with a 400K context window and 128K max output. It supports text and image input, text output, and a broad tool surface in the Responses API, including web search, file search, code interpreter, hosted shell, apply patch, skills, MCP, tool search, and computer use.

That tool support is part of what makes this model matter. GPT-5.4 mini is not just a cheaper chat route. It is built for orchestration-heavy systems where the model needs to inspect artifacts, call tools, and move work forward quickly.

Pricing & Access

Published API pricing is:

  • Input: $0.75 per 1M tokens
  • Output: $4.50 per 1M tokens

OpenAI also notes a 10% uplift for regional-processing endpoints. Outside the API, GPT-5.4 mini is available in Codex and ChatGPT, where it serves as a direct option or a fallback depending on plan tier.

Best Use Cases

Use GPT-5.4 mini for coding copilots, codebase-search subagents, document-processing assistants, and multimodal workflows that need stronger performance than GPT-5 mini without moving all the way to GPT-5.4. It is especially useful when a system benefits from many parallel smaller-model calls rather than one expensive frontier call.

Comparisons

  • GPT-5.4 (OpenAI): Higher-capability premium route for harder professional tasks, but far more expensive.
  • GPT-5 mini (OpenAI): Cheaper older mini tier, now clearly behind on coding and tool-heavy workloads.
  • GPT-5.4 nano (OpenAI): Lower-cost option for simpler support tasks, classification, and lightweight subagents.