GPT-3.5 Turbo

OpenAIMini

Legacy model. Still available but GPT-4.1 Nano is recommended instead.

Pricing

Input (per 1M tokens)

$0.50

Output (per 1M tokens)

$1.50

Cost Examples

Scenario	Cost
100 chat messages (500 in / 200 out each)	$0.0550
1K API calls (2K in / 500 out each)	$1.7500
10K short requests (200 in / 100 out each)	$2.5000
1M tokens input + 100K output	$0.6500

Capabilities

Context Window

16K

Max Output

4K

Speed

100 tok/s

Released

2023-03-01

NoVision

YesTool Use

YesStreaming

YesJSON Mode

API Details

Model IDgpt-3.5-turbo

API Endpointhttps://api.openai.com/v1/chat/completions

Last Updated2026-04-12

Other OpenAI Models

GPT-4.1Flagship

$2.00 in / $8.00 out per 1M tokens

GPT-4.1 MiniStandard

$0.40 in / $1.60 out per 1M tokens

GPT-4.1 NanoMini

$0.10 in / $0.40 out per 1M tokens

$2.50 in / $10.00 out per 1M tokens

GPT-4o MiniMini

$0.15 in / $0.60 out per 1M tokens

$2.00 in / $8.00 out per 1M tokens

o4-miniReasoning

$1.10 in / $4.40 out per 1M tokens

Open Cost Calculatorto compare GPT-3.5 Turbo costs with other models