Older model text price, per million tokens, checked 23 October 2026. Cached input is not listed, so it is billed as normal input. Context window: 16,385.
The batch row is listed for gpt-3.5-turbo-0125 at half this standard price.
$0.0011 for one request, and $0.06 a day at 50 requests a day.
Show the maths
New input: 1,000 tokens × $0.50 per million = $0.0005
Output: 400 tokens × $1.50 per million = $0.0006
1,500 requests a month × $0.0011 = $1.65
Batch processing would save about $0.83 a month
OpenAI's batch table lists half the standard input and output price for this model. Batch jobs are slower, and they suit work that can wait.
GPT-4.1 nano would cost about $1.26 less a month
It is a cheaper model in the same broad class on this price list. It is still a different model, and the replies will not match.
A reply half as long would save about $0.45 a month
Output tokens are often the expensive part. Asking for a shorter answer cuts that cost directly.
Cached prices here are read prices. Writing a cache can cost extra, and that write price is on the provider’s page, not in this total. A US-only endpoint is 1.1× at some providers and is not included. Fast modes are not included.
How much does GPT-3.5 Turbo cost?
GPT-3.5 Turbo is $0.50 per million input tokens and $1.50 per million output tokens on the standard price checked on the provider’s page. No cached-input price was listed, so cached tokens are billed at the normal input price.
What is the context window for GPT-3.5 Turbo?
The context window we could confirm is 16,385 tokens. That is the amount of text the model can hold in one request, input and output together, within the provider’s other limits.
Where does the GPT-3.5 Turbo price come from?
The figures were read from OpenAI’s pricing page on 23 October 2026: https://developers.openai.com/api/docs/pricing. If that page has changed since, the page is ahead of this site until the snapshot is updated.