GPT-4.1 nano vs GPT-4o (2024-11-20): API price and specs

GPT-4.1 nano is 98% cheaper than GPT-4o (2024-11-20) on input price.

GPT-4.1 nano is 98% cheaper than GPT-4o (2024-11-20) on output price.

GPT-4.1 nano is 98% cheaper than GPT-4o (2024-11-20) on a 1M-in / 200k-out workload.

GPT-4.1 nano has a 718.4% larger context than GPT-4o (2024-11-20).

Field	GPT-4.1 nano	GPT-4o (2024-11-20)
Lowest input, per 1M	$0.05	$2.50 +4900%
Median input, per 1M	$0.10	$2.50 +2400%
Lowest output, per 1M	$0.20	$10.00 +4900%
Median output, per 1M	$0.40	$10.00 +2400%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.09	$4.50 +4900%
Context	1M	128K +87.8%
Max output	943K	16K +98.3%
Providers	21	8 +61.9%
Regions	EU, GLOBAL, US	US
Accepts	file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text	file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	openrouter	aihubmix

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

aihubmix, edenai, fastrouter, kilo, openai, openrouter, orcarouter, requesty

Frequently asked questions

Which is cheaper, GPT-4.1 nano or GPT-4o (2024-11-20)?

GPT-4.1 nano is 98% cheaper than GPT-4o (2024-11-20) on input price. GPT-4.1 nano is 98% cheaper than GPT-4o (2024-11-20) on output price. GPT-4.1 nano is 98% cheaper than GPT-4o (2024-11-20) on a 1M-in / 200k-out workload.

Which has the larger context, GPT-4.1 nano or GPT-4o (2024-11-20)?

GPT-4.1 nano: 1M tokens; GPT-4o (2024-11-20): 128K tokens.

Where can I use both GPT-4.1 nano and GPT-4o (2024-11-20)?

aihubmix, edenai, fastrouter, kilo, openai, openrouter, orcarouter, requesty