TheToolRadar

GPT-3.5 Turbo API Cost Calculator

Estimate your monthly API costs for GPT-3.5 Turbo from Openai.

Pricing per 1M tokens

Input
$0.5000
Output
$1.50
16.4K context4.1K max outputFunction callingStreaming

Pricing last verified: Mar 21, 2026

30-Day Price History

Solid line: input price  ·  Dashed line: output price

Estimate Your Costs

What are you building?

Cost Breakdown

Input cost/request$0.000250
Output cost/request$0.000450
Cost per request$0.000700
Daily cost (1,000 requests)$0.7000
Monthly estimate$21.00
Annual estimate$252.00

Compare with Similar Models

ModelInput/1MOutput/1M
GPT-4.1 Mini
Openai
$0.4000$1.60
GPT-IMAGE-1-MINI
Openai
$2.00$0.2000
GPT-5 Mini
Openai
$0.2500$2.00
GPT-5.1-Codex-Mini
Openai
$0.2500$2.00
GPT-5.4 Nano
Openai
$0.2000$1.25

Frequently Asked Questions

How much does GPT-3.5 Turbo cost per token?

GPT-3.5 Turbo is priced at $0.5000 per 1M input tokens and $1.50 per 1M output tokens. Use the calculator above to estimate your monthly costs based on your usage volume.

What is the context window for GPT-3.5 Turbo?

GPT-3.5 Turbo has a context window of 16.4K tokens (16,385 tokens). The maximum output length is 4.1K tokens.

Does GPT-3.5 Turbo support function calling (tool use)?

Yes, GPT-3.5 Turbo supports function calling (also called tool use). You can define custom functions that the model can invoke as part of its responses.

How does GPT-3.5 Turbo compare to similar models?

GPT-3.5 Turbo costs $0.5000 input and $1.50 output per 1M tokens. GPT-5.4 Nano is less expensive at $0.2000 input and $1.25 output per 1M tokens. See the "Compare with Similar Models" table above, or visit the GPT-5.4 Nano page at /tools/cost-calculator/openai/gpt-5-4-nano.