GPT-4o

Name: GPT-4o
Author: OpenAI

proprietary

GPT-4o (“o” for “omni”) is our versatile, high-intelligence flagship model.

Intelligence

Speed

Context

128K

Max output

16K

Input price

$2.5/1M tokens

Output price

$10/1M tokens

Snapshotsgpt-4o-2024-11-20 gpt-4o-2024-08-06 gpt-4o-2024-05-13

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

ProviderOpenAI

Creatoropenai

Familygpt-4o

Licenseproprietary

Parameters—

Statusactive

Input modalitiestext, image

Output modalitiestext

Architecture—

Knowledge cutoff2023-10

Training data cutoff—

Release date2024-11-20

Deprecation date—

Typechat

Reasoning tokens—

Max input—

Open weightNo

Sourceofficial

Last updated2026-03-26

Tools

Function Callingfunction_calling

Call external functions and APIs

Endpoints

Chat CompletionsPOST

Generate chat responses with messageshttps://api.openai.com/v1/chat/completions

ResponsesPOST

Stateful multi-turn conversationshttps://api.openai.com/v1/responses

AssistantsPOST

Persistent assistants with tools and fileshttps://api.openai.com/v1/assistants

BatchPOST

Async batch processing at lower costhttps://api.openai.com/v1/batches

Pricing

Fine-tuning

	Training	Input	Cached input	Output
Standard	$25	$3.75	$1.875	$15
Batch	—	$1.875	—	$7.5

Family Comparison: gpt-4o

Model	Caps	Context	Max out	Pricing
GPT-4o mini Audio	TS	128K	16K	$0.15$0.6
GPT-4o mini Search Preview	VS	128K	16K	$0.15$0.6
GPT-4o mini	VTS	128K	16K	$0.15$0.6
GPT-4o mini Realtime	T	16K	4K	$0.6$2.4
GPT-4o mini TTS		—	—	$0.6—
GPT-4o mini Transcribe		16K	2K	$1.25$5
GPT-4o Audio	TS	128K	16K	$2.5$10
GPT-4o Search Preview	VS	128K	16K	$2.5$10
GPT-4o Transcribe Diarize		16K	2K	$2.5$10
GPT-4o Transcribe		16K	2K	$2.5$10
GPT-4o	VTS	128K	16K	$2.5$10
GPT-4o Realtime	T	32K	4K	$5$20

API

GET/v1/models/openai/gpt-4o