GPT-4 Turbo vs GPT-4.1 mini: API price and specs

GPT-4.1 mini is 96% cheaper than GPT-4 Turbo on input price.

GPT-4.1 mini is 95% cheaper than GPT-4 Turbo on output price.

GPT-4.1 mini is 96% cheaper than GPT-4 Turbo on a 1M-in / 200k-out workload.

GPT-4.1 mini has a 718.4% larger context than GPT-4 Turbo.

Field	GPT-4 Turbo	GPT-4.1 mini
Lowest input, per 1M	$5.00 +2400%	$0.20
Median input, per 1M	$10.00 +2400%	$0.40
Lowest output, per 1M	$15.00 +1775%	$0.80
Median output, per 1M	$30.00 +1775%	$1.60
Lowest unit price	—	—
Cost of 1M in + 200k out	$8.00 +2122.2%	$0.36
Context	128K +87.8%	1M
Max output	4K +87.5%	33K
Providers	12 +47.8%	23
Regions	US	EU, GLOBAL, US
Accepts	file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text	application/pdf, 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	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

aihubmix, azure, edenai, fastrouter, impossibl, kilo, openai, openrouter, orcarouter, poe, trustedrouter, vercel

Frequently asked questions

Which is cheaper, GPT-4 Turbo or GPT-4.1 mini?

GPT-4.1 mini is 96% cheaper than GPT-4 Turbo on input price. GPT-4.1 mini is 95% cheaper than GPT-4 Turbo on output price. GPT-4.1 mini is 96% cheaper than GPT-4 Turbo on a 1M-in / 200k-out workload.

Which has the larger context, GPT-4 Turbo or GPT-4.1 mini?

GPT-4 Turbo: 128K tokens; GPT-4.1 mini: 1M tokens.

Where can I use both GPT-4 Turbo and GPT-4.1 mini?

aihubmix, azure, edenai, fastrouter, impossibl, kilo, openai, openrouter, orcarouter, poe, trustedrouter, vercel