GPT-3.5 Turbo - In-Depth Overview

OpenAI · GPT-3.5

outdated

Model ID: gpt-3.5-turbo

Get all the details on GPT-3.5 Turbo, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as chat, fine_tuning, streaming, available API code samples, and performance strengths.

Key Metrics

Input Limit

16.4K tokens

Output Limit

4.1K tokens

Input Cost

$0.50/1M

Output Cost

$1.50/1M

Sample API Code

from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Required Libraries

openai

Benchmarks

Benchmark	Score	Source	Notes
lmarena text	1103	lmarena.ai	Score for gpt-3.5-turbo-0125 snapshot
lmarena text	1065	lmarena.ai	Score for gpt-3.5-turbo-1106 snapshot

Notes

Legacy GPT model optimized for chat using the Chat Completions API, but also works well for non-chat tasks. As of July 2024, gpt-4o-mini is recommended as a cheaper, more capable, multimodal, and faster alternative. GPT-3.5 Turbo is still available for use in the API. Supports snapshots for consistent performance.