GPT-4.1 nano pricing.
Prices checked
GPT-4.1 nano costs $0.10 in and $0.40 out per million tokens from OpenAI; the cheapest price is $0.16 at Poe, checked .
OpenAI's own price
OpenAI
$0.10 in · $0.40 out
80% below the typical price of the 392 text models we track.
Cheapest price
Poe
$0.09 in · $0.36 out
10% 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 nano
- 1
$0.09 in · $0.36 out
$0.16/M tokens - 2
$0.10 in · $0.38 out
$0.17/M tokens - 3
$0.10 in · $0.40 out
$0.18/M tokens - 4
$0.10 in · $0.40 out
$0.18/M tokens - 5
$0.10 in · $0.40 out
$0.18/M tokens - 6
$0.10 in · $0.40 out
$0.18/M tokens - 7
$0.10 in · $0.40 out
$0.18/M tokens - 8
$0.10 in · $0.40 out
$0.18/M tokens - 9
$0.10 in · $0.40 out
$0.18/M tokens - 10Same as maker
$0.10 in · $0.40 out
$0.18/M tokens - 11
SAP AI Core
Same as maker$0.10 in · $0.40 out
$0.18/M tokens - 12
$0.10 in · $0.40 out
$0.18/M tokens - 13
$0.10 in · $0.40 out
$0.18/M tokens - 14
$0.10 in · $0.40 out
$0.18/M tokens - 15
$0.10 in · $0.40 out
$0.18/M tokens - 16
$0.10 in · $0.40 out
$0.18/M tokens - 17
$0.10 in · $0.40 out
$0.18/M tokens - 18
$0.10 in · $0.40 out
$0.18/M tokens - 19
$0.10 in · $0.40 out
$0.18/M tokens - 20
$0.10 in · $0.40 out
$0.18/M tokens - 21
$0.10 in · $0.40 out
$0.18/M tokens - 22
$0.10 in · $0.40 out
$0.18/M tokens - 23
$0.11 in · $0.44 out
$0.19/M tokens - 24
$0.11 in · $0.44 out
$0.19/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 nano does, cheapest first. Each percentage is against GPT-4.1 nano's cheapest price, $0.16 per M tokens.
Qwen3.8 Flash
1M context · 41 providers
Alibaba Cloud (China)$0.19/M tokens20% moreClaude Haiku 5.5
1M context · 42 providers
OpenRouter$0.20/M tokens27% moreMiniMax-M3.1-Flash
1M context · 39 providers
StreamLake$0.24/M tokens50% moreGemini 3.1 Flash Lite
1M context · 37 providers
Kilo Gateway$0.28/M tokens79% more
Frequently asked
- Who sells GPT-4.1 nano cheapest?
- Poe, at $0.09 in and $0.36 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 nano 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 nano hold?
- 1,047,576 tokens in one call, which is about 1M, and it can call your own functions.
- How does GPT-4.1 nano compare with the rest of the market?
- At $0.18 per million tokens, OpenAI's own price is 80% below the typical $0.88 across the 392 text models we track.
More from OpenAI