Skip to model information

GPT-4o

Available

An OpenAI model with a 128K-token context window, image input and tool calling. On the OpenAI API since May 13, 2024.

Access details: OpenAI API

An alias. The provider can point it at a newer version.

gpt-4o
Updated Sep 23, 2026

Capabilities & limits

Context window
128K
Maximum output
16K
Image input
Supported
Tool calling
Supported
Structured output
Supported

Pricing

USD / 1M tokens
Input
$2.50
Output
$10.00

Standard rates per million tokens. Discounts and long-context rates, where offered, are on OpenAI's pricing page.

Full rate card 3 rates

All prices in USD.

Standard input

$2.50 per 1M tokens

Standard output

$10.00 per 1M tokens

Cached input

$1.25 per 1M tokens

Other tiers per 1M tokens (short context): Batch: $1.25 input / $5 output; Fast mode: $4.25 input / $17 output / $2.125 cached.

Price history
Sep 23, 2026

Input $2.50 per million tokens

Sep 23, 2026

Output $10.00 per million tokens

Technical details

Parameters
Not published
Active parameters
Not published
Architecture
Not published
Training / knowledge cutoff
Oct 01, 2023
Input modalities
Text, image
Output modalities
Text

Release & lifecycle

First available
May 13, 2024
available
As of Sep 23, 2026

Considering a switch?

Specs only go so far. Try both on your own tasks and compare quality, speed and cost.

Compare with Kimi K3 →

Prices and availability as of October 20, 2026. OpenAI's own pages have the latest.