What it costs
Per million tokens (How model prices are quoted: dollars per million tokens, charged separately for what you send and what comes back.), in USD, as published..
| Charge | Per million tokens | What it is |
|---|---|---|
| Input (The unit a model reads and writes. Roughly three quarters of an English word, so 1,000 tokens is about 750 words.) | $1.75 | Every token you send. |
| Output (The unit a model reads and writes. Roughly three quarters of an English word, so 1,000 tokens is about 750 words.) | $14 | Every token it generates. |
| Cache read (Paying a reduced rate for a prefix the vendor has already processed, instead of full price for sending it again.) | $0.175 | An input token served from the cache instead of being charged in full. |
| Cache write, 5 minutes (The charge for putting a prefix into the prompt cache. Usually more than the input rate, not less.) | not published | Putting tokens into a cache that lives five minutes. |
| Cache write, 1 hour (The charge for putting a prefix into the prompt cache. Usually more than the input rate, not less.) | not published | The same, for an hour. Usually the biggest line on an agentic bill. |
2 rows above say “not published”: OpenAI does not state those figures on the page we read, so we do not either. The cost calculator will refuse to price a workload that needs one of them rather than quietly estimating it.
What it can do
The page we read does not state this model’s capabilities, so we do not list any. That is a gap in what we know, not a claim that it cannot do these things.
Not stated either way: Tool use, Reads images, Makes images, Reads audio, Reads video, Computer use.
Catalogue last refreshed 2026-10-10.How we verify a price.