gpt-5.4

Name: gpt-5.4
Author: Vercel AI Gateway

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

Show unsupported (2)

Reasoning & Interaction

Reasoning

Tool Calling

Output Control

Structured Output

JSON Mode

Infrastructure

Streaming

Batch Processing

Details

ProviderVercel AI Gateway

CreatorOpenAI

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 cutoff2025-08

Release date2026-03-05

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

Model	Caps	Perf	Speed	Context	Max out	Pricing
gpt-5.4-nano	RTJJMSB	—	—	400K	128K	$0.2$1.25
gpt-5.4-mini	RTJJMSB	—	—	400K	128K	$0.75$4.5
gpt-5.4	RTJJMSB	—	—	1.1M	128K	$2.5$15
gpt-5.4-pro	RTS	—	—	1.1M	128K	$30$180

API

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