RealCloudCost

ai apis / openai / openai api

What the OpenAI API really costs

200,000 requests a month to a model cost $0.00 a month, or $0 a year.

list prices, read from the providers' pages · checked 17 november 2026 · sources

Start from a typical use then change anything in the form below

spec sheet gpt-6.1-solchecked 2026-11-17

model provider

  1. 01Input tokens [1]$0.00largest
  2. 02Cached input tokens [1]$0.00largest
  3. 03Output tokens [1]$0.00largest
Total, a month$0.00

a year $0

setup formyou write in blue

Your setup change any box, the sheet follows

the sheet on the right updates as you writethe sheet above updates as you write

Why the bill is bigger than expected

Output costs five times input. GPT models charge about five times more for each token they write than for each token they read. Reasoning tokens the model uses to think count as output.

Cached input costs a tenth. Repeated prompt prefixes, such as a long system prompt, are cached automatically and billed at a tenth of the input price when reused.

Batch costs half. Requests sent through the Batch API are billed at half the standard price, for results returned within 24 hours.

Sources

  1. [1]OpenAI API prices per million tokens, standard, cached and batch, as published. platform.openai.com/docs/pricing, read 2026-11-17.

Prices are list prices in USD per million tokens, before tax, credits or committed-use discounts. They are kept by hand from each provider's pricing page and confirmed against it every night; a price that no longer matches blocks the site from updating. Cache writes, tools such as web search, images, audio and fine-tuning are not counted. The calculator runs in your browser; nothing you type is sent anywhere.