computer-use-preview

Model Overview

computer-use-preview is a specialized model trained to understand and execute computer tasks.

Key Features

Average reasoning (2/4 bulbs rating)
Slow speed (2/5 lightning bolts rating)
Specialized model for computer use tool
8,192 context window
1,024 max output tokens
Knowledge cutoff: Oct 01, 2023
Reasoning token support

Technical Specifications

Pricing: Input: $3.00 per 1M tokens; Output: $12.00 per 1M tokens; Additional fee per tool call
Supports: Input: text and image; Output: text only
Features: Computer use via Responses API

Snapshots

computer-use-preview
computer-use-preview-2025-03-11

Positioning and Use Cases

The computer-use-preview model is a specialized model for the computer use tool. It is trained to understand and execute computer tasks. This model is only usable in the Responses API.

Rate Limits

Free tier: Not supported
Tier 1: Not supported
Tier 2: Not supported
Tier 3: 3,000 RPM, 20,000,000 TPM
Tier 4: 3,000 RPM, 20,000,000 TPM
Tier 5: 3,000 RPM, 20,000,000 TPM

Documentation

Official Documentation

OpenAI

Pioneer in AI, globally renowned for GPT series models

computer-use-preview

Parameters Unknow

Output tokens 1,024 tokens

computer-use-preview Specialized model for computer use tool

Official: $3 • $12 Our Price: $2.4 • $9.6 Save 20%

Back To List Try Now

Frequently Asked Questions

What is the uptime guarantee?

We guarantee 99.9% uptime with our enterprise-grade infrastructure and redundant systems.

How is pricing calculated?

Pricing is based on the number of tokens processed. Both input and output tokens are counted in the final cost.

What is the difference between GPT-4 and GPT-4 Turbo?

GPT-4 Turbo is the latest version with improved performance, longer context window, and more recent knowledge cutoff date.