Skip to model information

GPT-4.1

Available

An OpenAI model with a 1,047,576-token context window, image input and tool calling. On the OpenAI API since April 14, 2025.

Access details: OpenAI API

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

gpt-4.1
Updated Sep 23, 2026

Capabilities & limits

Context window
1,047,576
Maximum output
32K
Image input
Supported
Tool calling
Supported
Structured output
Supported

Pricing

USD / 1M tokens
Input
$2.00
Output
$8.00

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

$2.00 per 1M tokens

Standard output

$8.00 per 1M tokens

Cached input

$0.50 per 1M tokens

Other tiers per 1M tokens (short context): Batch: $1 input / $4 output; Fast mode: $3.5 input / $14 output / $0.875 cached.

Price history
Sep 23, 2026

Input $2.00 per million tokens

Sep 23, 2026

Output $8.00 per million tokens

Technical details

Parameters
Not published
Active parameters
Not published
Architecture
Not published
Training / knowledge cutoff
Jun 01, 2024
Input modalities
Text, image
Output modalities
Text

Release & lifecycle

First available
Apr 14, 2025
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 Claude Sonnet 5.5 →

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