Free calculator
OpenAI API pricing calculator
Your monthly OpenAI bill on each model at OpenAI's list prices, including the cache write rate that GPT-5.6 and the GPT-6 models charge and older models don't.
How much does the OpenAI API cost? (prices checked 2026-10-26)
gpt-6.1-sol costs $2 per million input tokens and $10 per million output tokens, gpt-6-luna $0.10 and $0.50, and gpt-6-astra $10 and $50. On GPT-5.6 and every GPT-6 model, writing a prompt to the cache costs 1.25 times the input price (2.5 times for a 12-hour cache) and reading it back costs a tenth. Batch and Flex are half price, Fast is double, and web search is $10 per 1,000 calls.
| Model | Input | Of which writes | Output | Per month |
|---|
List prices from developers.openai.com/api/docs/pricing, checked 2026-10-26; global processing (data residency endpoints add 10% for models released since March 5, 2026); prompts up to 272k tokens; 30-day month. Cache writes use the default 30-minute lifetime and apply only to GPT-5.6 and GPT-6 models; on older models those tokens are billed as normal input. Web search is $10 per 1,000 calls; the search content tokens it adds to the prompt are not counted here. gpt-5.6-sol is on promotional pricing until at least November 21, 2026.
Why this line grows
The cache write. On GPT-5.6 and later, OpenAI's default (implicit) caching puts the cache breakpoint at the end of the latest user message, so the new part of every request is written to the cache at 1.25 times the input price, whether anything reads it again or not. For a one-shot endpoint that never repeats its input, that is a 25% surcharge on the uncached input. Set the second percentage to 100 for implicit mode, or lower it to see explicit mode, where you place the breakpoint after the part that really repeats and the rest is billed at the plain input rate.
The other thing the table shows: last year's budget models are no longer the budget option. gpt-6-luna is cheaper than gpt-4o-mini and gpt-5.4-mini on both input and output.
Our OpenAI API pricing post walks through a real workload line by line. The LLM API cost calculator puts the same traffic next to Claude and Gemini, and the Gemini API pricing calculator shows Google's announced increases.
If your AI bill grew faster than your users, send us the usage page.