← Back to all models

GPT-5.4

OpenAILarge Language ModelProprietary

OpenAI's most capable frontier model optimized for agentic, coding, and professional workflows. Features native computer-use capabilities, 1M token context, and the most token-efficient reasoning of the GPT-5 family.

Abilities

Text GenerationCode GenerationReasoningMathVisionFunction CallingStructured OutputMultilingualLong Context

Use Cases

ChatbotCoding AssistantContent WritingData AnalysisResearchEnterpriseAutomation

Available in Tools

Availability

ChatGPT Mobile
Azure OpenAI

How to Use

Access via the OpenAI API using the `gpt-5.4` model ID. Available through ChatGPT (Plus, Pro, Enterprise), Azure OpenAI, and major IDE integrations. Supports configurable reasoning effort levels (none/low/medium/high/xhigh).

Pros

  • Native computer-use capabilities — first general-purpose model that can operate software across applications
  • 1M token context window with 128K max output — handles entire codebases and book-length documents
  • Most token-efficient reasoning model — uses significantly fewer tokens than GPT-5.2 to solve problems
  • 33% fewer false claims and 18% fewer erroneous responses compared to GPT-5.2
  • State-of-the-art coding capabilities incorporating GPT-5.3-Codex advances
  • Configurable reasoning effort (none/low/medium/high/xhigh) — tune speed vs. depth per request

Cons

  • Closed source — no visibility into model weights, training data, or architecture
  • Expensive at scale ($2.50 input / $15.00 output per 1M tokens), especially for high-volume processing
  • Requests exceeding 272K tokens are priced at 2x input and 1.5x output
  • Knowledge cutoff August 2025 — cannot access real-time information without tools

What to Use It For

star

Perfect For

Agentic coding and professional workflows

First model with native computer-use + state-of-the-art coding in one package, top of APEX-Agents benchmark

Complex professional tasks (financial models, legal analysis)

Strongest factuality and reasoning capabilities with configurable effort levels

Large codebase analysis and refactoring

1M context window can hold entire codebases with 128K output for comprehensive changes

thumb_up

Good For

Enterprise AI applications

Available on Azure with compliance certifications and the largest tool ecosystem

Multi-step reasoning and research

Configurable reasoning effort allows tuning depth vs. speed per request

warning

Not Recommended

Simple high-throughput tasks

Overkill and expensive — use GPT-4.1 Mini or Nano for lightweight tasks

Try instead: GPT-4.1 Mini, GPT-4.1 Nano

Self-hosting or offline use

Closed source with no available weights — completely dependent on OpenAI API

Try instead: Llama 4 Maverick, Qwen 3

block

Do Not Use For

Image generation

It is an LLM, not an image generation model

Try instead: GPT-Image-1, FLUX.2 Pro

Video generation

Text and reasoning model only — cannot create video content

Try instead: Sora, Veo

Technical Details

Pricing$2.50 / 1M input tokens, $15.00 / 1M output tokens
ParametersUndisclosed
detail.contextWindow1M tokens

Links