Back to all models

GPT-4 Turbo

OpenAI · GPT-4

Default

Key Metrics

Input Limit

128K tokens

Output Limit

4.1K tokens

Input Cost

$10.00/1M

Output Cost

$30.00/1M

Sample API Code

Required Libraries

openai
openai

Notes

GPT-4 Turbo is the next generation of GPT-4, an older high-intelligence GPT model. It was designed to be a cheaper, better version of GPT-4. Today, we recommend using a newer model like GPT-4o. Described as having 'Average' intelligence and 'Medium' speed in a summary card. Snapshots available: gpt-4-turbo (points to gpt-4-turbo-2024-04-09), gpt-4-turbo-2024-04-09, gpt-4-turbo-preview (points to gpt-4-0125-preview), gpt-4-0125-preview, gpt-4-1106-vision-preview. Features not supported as per dedicated 'Features' section: Structured outputs, Fine-tuning, Distillation, Predicted outputs.

Capabilities

Text Generation
Image Input Processing
Streaming
Function Calling

Supported Data Types

Input Types

text
image

Output Types

text

Strengths & Weaknesses

Good at

High-intelligence tasks
Cost-effectiveness compared to older GPT-4
Large context window

Additional Information

Latest Update

Apr 9, 2024

Knowledge Cutoff

2023-12-01