GPT-4.1 nano vs o4-mini: API price and specs

GPT-4.1 nano is 91% cheaper than o4-mini on input price.

GPT-4.1 nano is 91% cheaper than o4-mini on output price.

GPT-4.1 nano is 91% cheaper than o4-mini on a 1M-in / 200k-out workload.

GPT-4.1 nano has a 423.8% larger context than o4-mini.

Field	GPT-4.1 nano	o4-mini
Lowest input, per 1M	$0.05	$0.55 +1000%
Median input, per 1M	$0.10	$1.10 +1000%
Lowest output, per 1M	$0.20	$2.20 +1000%
Median output, per 1M	$0.40	$4.40 +1000%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.09	$0.99 +1000%
Context	1M	200K +80.9%
Max output	943K	100K +89.4%
Providers	21	18 +14.3%
Regions	EU, GLOBAL, US	EU, US
Accepts	file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text	file, image, pdf, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	openrouter	openrouter

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

abacus, aihubmix, azure, cometapi, edenai, fastrouter, helicone, impossibl, jiekou, kilo, nearai, openai, openrouter, poe, requesty, trustedrouter, vercel, zenmux

Frequently asked questions

Which is cheaper, GPT-4.1 nano or o4-mini?

GPT-4.1 nano is 91% cheaper than o4-mini on input price. GPT-4.1 nano is 91% cheaper than o4-mini on output price. GPT-4.1 nano is 91% cheaper than o4-mini on a 1M-in / 200k-out workload.

Which has the larger context, GPT-4.1 nano or o4-mini?

GPT-4.1 nano: 1M tokens; o4-mini: 200K tokens.

Where can I use both GPT-4.1 nano and o4-mini?

abacus, aihubmix, azure, cometapi, edenai, fastrouter, helicone, impossibl, jiekou, kilo, nearai, openai, openrouter, poe, requesty, trustedrouter, vercel, zenmux