OpenAI

GPT-3.5-turbo

CTX16K

Retired

26Quality

Text

Input$0.50/M

Output$1.50/M

Compact GPT model for low-latency assistance and high-volume workloads

PaidProprietary201/1044

Drag to turn

OpenAITextCommonRetired

GPT-3.5-turbo

Compact GPT model for low-latency assistance and high-volume workloads

gpt-3.5-turbo

Type: Text
Quality: 26 · Top 74% on the Epoch Capabilities Index
Context window: 16,385 tokens
Max output: 4,096 tokens
Input price: $0.50 / 1M tokens
Output price: $1.50 / 1M tokens
Cache read: Free
Cache write: —
Released: Mar 1, 2023
Knowledge cutoff: Sep 2021
Takes in: Text
Puts out: Text
Reasoning: No
Tool calling: No
Structured output: No
File attachments: No
Access: Paid
License: Proprietary
Rarity: Common
Set number: 201/1044

Open OpenAI docs Quality 26 Where to run it 15 Evolution 3/12 Meet its creature Battle Gemini 3.1 Flash Lite

Weights aren’t public. Use is governed by OpenAI’s terms. Specs from models.dev, last changed Oct 19, 2026. Official source: platform.openai.com.

How good is it?

Public leaderboard scores for GPT-3.5-turbo, refreshed daily from Epoch AI and LMArena.

Top 74% of the 277 models on the Epoch Capabilities Index: #206.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Epoch Capabilities Index#206 of 277
One number fitted from dozens of hard benchmarks, from science questions to agentic coding.118.6 index
Listed as GPT-3.5 Turbo (Nov 2023)

Scores from Epoch AI, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

15 providers sell GPT-3.5-turbo through an API. Prices are per million tokens, cheapest first.

CheapestPoe$0.45 in · $1.40 out
From the labOpenAI$0.50 in · $1.50 out

API providers

Provider	Input	Output	Context
PoeCheapest paid`openai/gpt-3.5-turbo`	$0.45	$1.40	16K
DevPass (LLM Gateway)`gpt-3.5-turbo`	$0.50	$1.50	16K
Eden AI`openai/gpt-3.5-turbo`	$0.50	$1.50	16K
Impossibl`openai/gpt-3.5-turbo`	$0.50	$1.50	16K
Kilo Gateway`openai/gpt-3.5-turbo`	$0.50	$1.50	16K
LLM Gateway`openai/gpt-3.5-turbo`	$0.50	$1.50	16K
Merge Gateway`openai/gpt-3.5-turbo`	$0.50	$1.50	16K
NanoGPT`openai/gpt-3.5-turbo`	$0.50	$1.50	16K
OpenAIOfficial`gpt-3.5-turbo`	$0.50	$1.50	16K
OpenRouter`openai/gpt-3.5-turbo`	$0.50	$1.50	16K

Show 5 more providers

Provider	Input	Output	Context
OrcaRouter`openai/gpt-3.5-turbo`	$0.50	$1.50	16K
Vercel AI Gateway`openai/gpt-3.5-turbo`	$0.50	$1.50	16K
AI/ML API`openai/gpt-3.5-turbo`	$0.65	$1.95	16K
Azure`gpt-3.5-turbo-instruct`	$1.50	$2.00	4K
Azure Cognitive Services`gpt-3.5-turbo-instruct`	$1.50	$2.00	4K

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

GPT-3.5-turbo

GPT-3.5-turbo

How good is it?

Leaderboards

Where to run it

API providers

Face off

More from OpenAI

GPT-6.1 Sol

GPT-6 Sol

GPT-6 Luna

GPT-6 Astra

GPT-5.6 Terra

GPT-5.6 Sol

GPT-5.6 Luna

GPT-5.6