GPT-4o mini pricing.
Prices checked
GPT-4o mini costs $0.15 in and $0.60 out per million tokens from OpenAI; the cheapest price is $0.24 at Poe, checked .
OpenAI's own price
OpenAI
$0.15 in · $0.60 out
70% below the typical price of the 392 text models we track.
Cheapest price
Poe
$0.14 in · $0.55 out
9% less than OpenAI, and the provider says why.
Web search from this model costs $10 per 1,000 searches, plus its tokens; dedicated search APIs from $1
Every provider selling GPT-4o mini
- 1
$0.14 in · $0.55 out · 124k context here
$0.24/M tokens - 2
$0.15 in · $0.60 out
$0.26/M tokens - 3
$0.15 in · $0.60 out
$0.26/M tokens - 4
$0.15 in · $0.60 out
$0.26/M tokens - 5
$0.15 in · $0.60 out
$0.26/M tokens - 6Same as maker
$0.15 in · $0.60 out
$0.26/M tokens - 7
$0.15 in · $0.60 out
$0.26/M tokens - 8
$0.15 in · $0.60 out
$0.26/M tokens - 9
$0.15 in · $0.60 out
$0.26/M tokens - 10
$0.15 in · $0.60 out
$0.26/M tokens - 11Same as maker
$0.15 in · $0.60 out
$0.26/M tokens - 12
$0.15 in · $0.60 out
$0.26/M tokens - 13
$0.15 in · $0.60 out
$0.26/M tokens - 14
$0.15 in · $0.60 out
$0.26/M tokens - 15
$0.15 in · $0.60 out
$0.26/M tokens - 16
$0.15 in · $0.60 out
$0.26/M tokens - 17
$0.15 in · $0.60 out
$0.26/M tokens - 18
$0.15 in · $0.60 out
$0.26/M tokens - 19
$0.15 in · $0.60 out
$0.26/M tokens - 20
LowRouter
Same as maker$0.15 in · $0.60 out
$0.26/M tokens - 21
$0.15 in · $0.60 out · 131k context here
$0.26/M tokens - 22
$0.15 in · $0.60 out
$0.26/M tokens - 23$0.26/M tokens
- 24
$0.15 in · $0.60 out
$0.26/M tokens - 25
$0.15 in · $0.60 out
$0.26/M tokens
- 26
$0.15 in · $0.60 out
$0.26/M tokens - 27
$0.15 in · $0.60 out
$0.26/M tokens - 28
$0.16 in · $0.63 out
$0.28/M tokens - 29
$0.16 in · $0.64 out
$0.28/M tokens - 30
$0.17 in · $0.66 out
$0.29/M tokens - 31
$0.25 in · $1 out
$0.44/M tokens
Not ranked
Below the maker's own price with nothing published to account for it, from a catalog we could not read reliably, or a free tier, which is a limit rather than a price. Why
$0.07 in · $0.30 out
$0.13/M tokens$0.12 in · $0.48 out
$0.21/M tokens
What it costs for your work
A month at OpenAI's own price
A month at Poe, the cheapest
What you save
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
How we count
Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below OpenAI's own is listed as cheapest only when the provider says why.
- Resells
- The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Same as maker
- Sold by someone else at the price the maker charges.
- Maker's price
- What the lab that trained the model charges on its own API. Every other row is measured against it.
- Costs more
- Sold by someone else for more than the maker charges.
- Not ranked
- Below the maker's price on a closed model with nothing to account for it, or from a catalog we could not read reliably. Listed, and never a pick.
Similar models
Models from other labs that do what GPT-4o mini does, cheapest first. Each percentage is against GPT-4o mini's cheapest price, $0.24 per M tokens.
Frequently asked
- Who sells GPT-4o mini cheapest?
- Poe, at $0.14 in and $0.55 out per million tokens, checked 31 Oct 2026. The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Is GPT-4o mini open weights?
- No. OpenAI keeps the weights, so every price on this page is OpenAI's own or a resale of it. A price below OpenAI's here needs a published reason, or it is listed and not ranked.
- How much context does GPT-4o mini hold?
- 128,000 tokens in one call, which is about 128k, and it can call your own functions.
- How does GPT-4o mini compare with the rest of the market?
- At $0.26 per million tokens, OpenAI's own price is 70% below the typical $0.88 across the 392 text models we track.
More from OpenAI