GPT-3.5 Turbo

OpenAI

Good balance of speed and capability

Text Generation API GPT Family

Parameters

-

params

Context Window

16K

tokens

Max Output

4K

tokens

Input Price

$0.5

per 1M tokens

Output Price

$1.5

per 1M tokens

GPT Family 18 models

The full GPT line by generation — pricing and capabilities vary across the family.

GPT-5.5

GPT-5.5 Instant

Everyday assistant, low-latency chat

Hardest reasoning, research, complex coding

Agentic workflows, coding, research, data analysis

GPT-5.4

Complex reasoning, research, advanced analysis

General-purpose, reasoning, multimodal, document editing

GPT-5.3

Code generation, software engineering, reasoning

GPT-5

GPT-5.2 Thinking

GPT-5.2 Instant

Multimodal reasoning, reduced hallucinations

GPT-5.1

GPT-5.1 Instant

Fast, warm responses, customizable tone

GPT-5.1 Thinking

Complex reasoning, persistent problem-solving

GPT-4

GPT-4o (Nov 2024)

Multimodal, fast, versatile

Complex tasks, vision, analysis

Enterprise Azure integration

o1

Complex reasoning, math, code

STEM reasoning, efficient

GPT-3.5

GPT-3.5 Turbo Current

Fast, cost-effective

$0.5 / $1.5

in / out · 1M

Nov 2023

Capabilities

👁️

Vision

⚡

Function Calling

📋

JSON Mode

🌊

Streaming

💬

System Prompt

🖥️

Code Execution

🔍

Web Search

🔌

MCP Support

Details

Release Date: November 6, 2023
Knowledge Cutoff: January 1, 2022
Source: API
API Key Required: Yes
License: Proprietary
Model ID: gpt-3.5-turbo

Last updated: November 26, 2025