Skip to content
CountMyToken

OpenAI

GPT-5 nano costs $0.05 in and $0.40 out.

Older model text price, per million tokens, checked 23 October 2026. Cached input is $0.005 per million. Context window: 400,000.

Input
$0.05
Output
$0.40
Cached read
$0.005

API id: gpt-5-nano

Tell me when GPT-5 nano’s price changes

We’ll email a confirmation link. After you confirm, we write when this model’s listed price changes, and for that purpose only. You can remove the address here.

OpenAI pricing page · AI model prices

Price history, US dollars per million tokens
23 October 2026

Input $0.05Output $0.40

History starts with the snapshot checked on 23 October 2026. Earlier prices are left out unless an official page confirmed them.

Monthly cost

$0.32 a month with GPT-5 nano.

A month is 30 days. Prices last checked 23 October 2026.

The link stores these numbers. It does not store pasted text.

GPT-5 nano

Older model

$0.32 a month

$0.0002 for one request, and $0.01 a day at 50 requests a day.

Show the maths
  • New input: 1,000 tokens × $0.05 per million = $0.00005
  • Output: 400 tokens × $0.40 per million = $0.0002
  • 1,500 requests a month × $0.0002 = $0.32

  • Caching half the input would save about $0.03 a month

    That uses the published cache-read price of $0.005 per million tokens. It assumes half of these input tokens are already in a cache. Writing the cache can cost extra, and that write price is not included.

  • Batch processing would save about $0.16 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.

  • A reply half as long would save about $0.12 a month

    Output tokens are often the expensive part. Asking for a shorter answer cuts that cost directly.

Tell me when GPT-5 nano’s price changes

We’ll email a confirmation link. After you confirm, we write when this model’s listed price changes, and for that purpose only. You can remove the address here.

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-5 nano cost?

GPT-5 nano is $0.05 per million input tokens and $0.40 per million output tokens on the standard price checked on the provider’s page. Cached input, meaning tokens already stored and read back, is $0.005 per million tokens.

What is the context window for GPT-5 nano?

The context window we could confirm is 400,000 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-5 nano 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.