GPT-4o pricing at a glance
- Provider: OpenAI
- Input: $2.50 per million tokens
- Output: $10.00 per million tokens
- Cached input: $1.25 per million tokens
- Context window: 128,000 tokens
- Prices verified: September 24, 2026
About GPT-4o
GPT-4o costs $2.50 per million input tokens and $10 per million output, and its cached-input price of $1.25 is a 50% discount — a much smaller reduction than the 90% offered on newer OpenAI models, so caching saves less here. GPT-4o uses the o200k_base encoding and has a 128,000-token context window, so the token counts on this page are exact for it rather than estimates.
What GPT-4o costs in practice
A call with 1,000 input tokens and 500 output tokens costs $0.0075 on GPT-4o, so a thousand such calls cost $7.50. With prompt caching, a cache read is priced at $1.25 per million tokens, 50% below the standard input rate. Its 128k-token context window holds roughly 96,000 English words, or about 192 pages at 500 words a page; filling all of it once costs $0.32 in input tokens.
How this GPT-4o token counter counts tokens
GPT-4o uses OpenAI’s o200k_base encoding, and this page runs that tokenizer in your browser, so the count shown is exactly what the API will bill for the prompt text.
How to use it
- Paste your prompt into the box, or drop a .txt or .md file on it.
- Set the expected output length and how many calls you make per day.
- Compare the cost per call and per month across models; the cheapest is highlighted.
- Tick the cache option if your prompt prefix is reused, then copy the table if you need it elsewhere.
Frequently asked questions
How many tokens is my text in GPT-4o?
Paste it into the box above; the count shown for this model is exact because it uses the same o200k_base tokenizer the API applies.
How much does GPT-4o cost per million tokens?
$2.50 per million input tokens and $10.00 per million output tokens, with cached input at $1.25, as of September 24, 2026.
Is my prompt sent to a server?
No. Counting runs in a background thread in your browser. The site records only an anonymous counter such as how many models were compared, never the text you paste.
Prices verified September 24, 2026 from OpenAI’s pricing page. Confirm on the provider’s site before budgeting.