GPT-4 Turbo

OpenAI

The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.

Try Now

Capabilities

Tool Use

Image Input

Technical Specifications

Context Window

128,000 tokens

Max Output

4,096 tokens

Pricing

Token Costs (per 1M tokens)

Cache Miss Input

$10

Non-Reasoning Output

$30

Tool Costs (per 1K calls)

Web Search

$15

Code Execution

$0.19

Legacy

Made legacy on

Reason

Superseded by GPT-4o at half the cost with same intelligence

Recommended Replacement

GPT-5.4