GPT-4.1 mini pricing.
Prices checked
GPT-4.1 mini costs $0.40 in and $1.60 out per million tokens from OpenAI; the cheapest price is $0.64 at Poe, checked .
OpenAI's own price
OpenAI
$0.40 in · $1.60 out
21% below the typical price of the 392 text models we track.
Cheapest price
Poe
$0.36 in · $1.45 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-4.1 mini
- 1
$0.36 in · $1.45 out
$0.64/M tokens - 2
$0.40 in · $1.60 out
$0.70/M tokens - 3
$0.40 in · $1.60 out
$0.70/M tokens - 4
$0.40 in · $1.60 out
$0.70/M tokens - 5
$0.40 in · $1.60 out
$0.70/M tokens - 6Same as maker
$0.40 in · $1.60 out
$0.70/M tokens - 7
$0.40 in · $1.60 out
$0.70/M tokens - 8
$0.40 in · $1.60 out
$0.70/M tokens - 9
$0.40 in · $1.60 out
$0.70/M tokens - 10
$0.40 in · $1.60 out
$0.70/M tokens - 11Same as maker
$0.40 in · $1.60 out
$0.70/M tokens - 12
SAP AI Core
Same as maker$0.40 in · $1.60 out
$0.70/M tokens - 13
$0.40 in · $1.60 out
$0.70/M tokens - 14
$0.40 in · $1.60 out
$0.70/M tokens - 15
$0.40 in · $1.60 out
$0.70/M tokens - 16
$0.40 in · $1.60 out
$0.70/M tokens - 17
$0.40 in · $1.60 out
$0.70/M tokens - 18
$0.40 in · $1.60 out
$0.70/M tokens - 19
$0.40 in · $1.60 out
$0.70/M tokens - 20
$0.40 in · $1.60 out
$0.70/M tokens - 21
$0.40 in · $1.60 out
$0.70/M tokens - 22
$0.40 in · $1.60 out
$0.70/M tokens - 23
LowRouter
Same as maker$0.40 in · $1.60 out
$0.70/M tokens - 24
$0.40 in · $1.60 out
$0.70/M tokens - 25$0.70/M tokens
- 26
$0.40 in · $1.60 out
$0.70/M tokens - 27
$0.40 in · $1.60 out
$0.70/M tokens - 28
$0.40 in · $1.60 out · 128k context here
$0.70/M tokens - 29
$0.40 in · $1.60 out
$0.70/M tokens - 30
$0.40 in · $1.60 out
$0.70/M tokens - 31
$0.42 in · $1.69 out
$0.74/M tokens - 32
$0.44 in · $1.71 out
$0.75/M tokens - 33
$0.44 in · $1.76 out
$0.77/M tokens - 34
$0.70 in · $2.80 out
$1.22/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.
Similar models
Models from other labs that do what GPT-4.1 mini does, cheapest first. Each percentage is against GPT-4.1 mini's cheapest price, $0.64 per M tokens.
Frequently asked
- Who sells GPT-4.1 mini cheapest?
- Poe, at $0.36 in and $1.45 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-4.1 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-4.1 mini hold?
- 1,047,576 tokens in one call, which is about 1M, and it can call your own functions.
- How does GPT-4.1 mini compare with the rest of the market?
- At $0.70 per million tokens, OpenAI's own price is 21% below the typical $0.88 across the 392 text models we track.
More from OpenAI