OpenAI
GPT-3.5 Turbo
Fast and affordable model for everyday tasks
Function CallingStreaming
Context Length
16K
tokens
Input Cost
$0.50
per 1M tokens
Output Cost
$1.50
per 1M tokens
Model Overview
Key information about GPT-3.5 Turbo
Provider
OpenAI
Model Type
Text-only Language Model
Context Window
16,384 tokens
Availability
Available
Tags
fastlegacyaffordable