gpt-5.4

proprietary

GPT-5.4 is a flagship model for complex professional work. Learn more in our GPT-5.4 model guidance. Reasoning.effort supports: none (default), low, medium, high and xhigh.

Intelligence
Reasoning
Speed
Context
1.1M
Max output
128K
Input price
$2.5/1M tokens
Output price
$15/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Provider Vercel AI Gateway
Creator OpenAI
Familygpt-5.4
Licenseproprietary
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightNo
Parameters—
Architecture—
Context window1.1M tokens
Max input—
Max output128K tokens
Reasoning tokensYes
Knowledge cutoff
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$2.5
Output
$15
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: gpt-5.4

ModelContextMax outPricing
gpt-5.4-nano400K128K$0.2$1.25
gpt-5.4-mini400K128K$0.75$4.5
gpt-5.41.1M128K$2.5$15
gpt-5.4-pro1.1M128K$30$180

API

GET/v1/models/vercel/openai/gpt-5.4

gpt-5.4

GPT-5.4 is a flagship model for complex professional work. Learn more in our GPT-5.4 model guidance. Reasoning.effort supports: none (default), low, medium, high and xhigh.

Changes · 3 entries
openai/gpt-5.4updateb301ebeMar 23, 2026, 11:47 PM
modalitiesinput["text"]output["text"]
openai/gpt-5.4update2b100acMar 23, 2026, 05:30 AM
model_typechat
tools["function_calling"]
openai/gpt-5.4create7f5c66fMar 21, 2026, 05:16 AM