GPT-5 Mini vs o3-mini: API price and specs

GPT-5 Mini is 77% cheaper than o3-mini on input price.

GPT-5 Mini is 55% cheaper than o3-mini on output price.

GPT-5 Mini is 67% cheaper than o3-mini on a 1M-in / 200k-out workload.

GPT-5 Mini has a 100% larger context than o3-mini.

Field	GPT-5 Mini	o3-mini
Lowest input, per 1M	$0.12	$0.55 +340%
Median input, per 1M	$0.25	$1.10 +340%
Lowest output, per 1M	$1.00	$2.20 +120%
Median output, per 1M	$2.00	$4.40 +120%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.33	$0.99 +204.6%
Context	400K	200K +50%
Max output	128K	100K +21.9%
Providers	27	18 +33.3%
Regions	EU, GLOBAL, US	GLOBAL
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, digitalocean, edenai, fastrouter, helicone, impossibl, jiekou, kilo, nearai, openai, openrouter, poe, requesty, trustedrouter, vercel

Frequently asked questions

Which is cheaper, GPT-5 Mini or o3-mini?

GPT-5 Mini is 77% cheaper than o3-mini on input price. GPT-5 Mini is 55% cheaper than o3-mini on output price. GPT-5 Mini is 67% cheaper than o3-mini on a 1M-in / 200k-out workload.

Which has the larger context, GPT-5 Mini or o3-mini?

GPT-5 Mini: 400K tokens; o3-mini: 200K tokens.

Where can I use both GPT-5 Mini and o3-mini?

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