gpt-3.5-turbo pricing

gpt-3.5-turbo from OpenAI costs $0.500 per 1M input tokens and $1.50 per 1M output tokens. Context window 16,385 tokens.

API id gpt-3.5-turbo · OpenAI · source · updated 2026-08-11

$0.500
Input / 1M tokens
$1.50
Output / 1M tokens
Cached input / 1M
16K
Context window

What gpt-3.5-turbo costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.0013
Document summary50,0002,000$0.03
1M tokens in, 200K out1,000,000200,000$0.80

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Common questions

How much does gpt-3.5-turbo cost per 1M tokens?
gpt-3.5-turbo costs $0.500 per 1M input tokens and $1.50 per 1M output tokens on the standard tier.
What is gpt-3.5-turbo's context window?
gpt-3.5-turbo accepts up to 16,385 tokens in a single request, and can return up to 4,096 output tokens.
Is there a cheaper OpenAI model than gpt-3.5-turbo?
Yes. gpt-4o-mini-2024-07-18 is $0.300 per 1M input tokens versus $0.500 for gpt-3.5-turbo, with a 128,000 token context window.
Where does this gpt-3.5-turbo price come from?
Directly from OpenAI's published pricing page, re-read every day and normalized to USD per 1,000,000 tokens.

Other OpenAI models

See all OpenAI pricing →