GPT-4o mini vs GPT-5 Mini: API price and specs

GPT-4o mini is 40% cheaper than GPT-5 Mini on input price.

GPT-4o mini is 70% cheaper than GPT-5 Mini on output price.

GPT-4o mini is 58% cheaper than GPT-5 Mini on a 1M-in / 200k-out workload.

GPT-5 Mini has a 212.5% larger context than GPT-4o mini.

Field	GPT-4o mini	GPT-5 Mini
Lowest input, per 1M	$0.075	$0.12 +66.7%
Median input, per 1M	$0.15	$0.25 +66.7%
Lowest output, per 1M	$0.30	$1.00 +233.3%
Median output, per 1M	$0.60	$2.00 +233.3%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.14	$0.33 +140.7%
Context	128K +68%	400K
Max output	16K +87.2%	128K
Providers	22 +18.5%	27
Regions	EU, GLOBAL, US	EU, GLOBAL, US
Accepts	application/pdf, 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	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, aiml, azure, cometapi, cortecs, digitalocean, edenai, fastrouter, helicone, impossibl, kilo, meganova, ofox, openai, openrouter, orcarouter, poe, requesty, trustedrouter, vercel, zenmux

Frequently asked questions

Which is cheaper, GPT-4o mini or GPT-5 Mini?

GPT-4o mini is 40% cheaper than GPT-5 Mini on input price. GPT-4o mini is 70% cheaper than GPT-5 Mini on output price. GPT-4o mini is 58% cheaper than GPT-5 Mini on a 1M-in / 200k-out workload.

Which has the larger context, GPT-4o mini or GPT-5 Mini?

GPT-4o mini: 128K tokens; GPT-5 Mini: 400K tokens.

Where can I use both GPT-4o mini and GPT-5 Mini?