Skip to model information

computer-use-preview

Retired

An OpenAI model with a 8K-token context window, image input and tool calling. Released on the OpenAI API March 11, 2025, now retired.

Access details: OpenAI API

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

computer-use-preview
Updated Sep 23, 2026

Capabilities & limits

Context window
8K
Maximum output
1K
Image input
Supported
Tool calling
Supported
Structured output
Unsupported

Pricing

USD / 1M tokens
Input
No longer sold
Output
No longer sold

No longer sold on the OpenAI API.

Price history
Jul 23, 2026

Input No longer sold per million tokens

Jul 23, 2026

Output No longer sold 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
Mar 11, 2025
deprecated
As of Sep 13, 2026
retired
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 Gemini 2.5 Pro →

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