GPT-4o mini pricing and token costs
GPT-4o mini 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
The cheapest input rate in the entire catalogue at $0.15 per million, sharing GPT-4o's 128,000-token window and its four-to-one output ratio. Reach for it when volume is the problem rather than window size — at this rate a prompt has to be very large before its cost is worth reasoning about at all. The trade is the ceiling: anything beyond 128,000 tokens needs a different model regardless of how cheap this one is.
Pricing
- Input, per 1M tokens
- $0.15
- Output, per 1M tokens
- $0.60
- 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 mini cost per million tokens?
- $0.15 per million input tokens and $0.60 per million output tokens.
- What is the context window of GPT-4o mini?
- 128,000 tokens, covering input and output combined.
- Which tokenizer does GPT-4o mini use?
- GPT-4o mini 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.