GPT-4o pricing and token costs
GPT-4o is a OpenAI model with a 128,000-token context window. Rates below are per million tokens, and are the ones in effect today.
In practice
A 128,000-token window at $2.50 per million input, with output at four times input rather than the six charged across the GPT-5.6 line — so answers cost proportionally less here than on the newer OpenAI models. The window is the real constraint: 128,000 tokens is roughly an eighth of what the 5.6 models or the Gemini line accept, so long documents will not fit at any price. Within that ceiling there is no long-context surcharge, so the rate stays flat from the first token to the last.
Pricing
- Input, per 1M tokens
- $2.50
- Output, per 1M tokens
- $10.00
- Context window
- 128,000 tokens
- Tokenizer
- o200k_base
Input and output combined.
Counted exactly, in your browser.
Alternatives
Head to head
Articles that quote these figures
Common questions
- How much does GPT-4o cost per million tokens?
- $2.50 per million input tokens and $10.00 per million output tokens.
- What is the context window of GPT-4o?
- 128,000 tokens, covering input and output combined.
- Which tokenizer does GPT-4o use?
- GPT-4o uses the o200k_base encoding. Counts are computed in your browser with the same tokenizer OpenAI publishes, so they are exact.
Figures come from OpenAI’s published list prices and are checked against every article on this site that quotes them at build time. They are still estimates of what a request costs — verify against your own billing before committing to them. See the methodology page for how these numbers are actually calculated.