GPT-5.3 Codex vs GPT-5.4: API price and specs

GPT-5.4 is 46% cheaper than GPT-5.3 Codex on input price.

GPT-5.4 is 46% cheaper than GPT-5.3 Codex on output price.

GPT-5.4 is 46% cheaper than GPT-5.3 Codex on a 1M-in / 200k-out workload.

GPT-5.4 has a 162.5% larger context than GPT-5.3 Codex.

Field	GPT-5.3 Codex	GPT-5.4
Lowest input, per 1M	$1.40 +86.7%	$0.75
Median input, per 1M	$1.75	$2.50 +42.9%
Lowest output, per 1M	$11.20 +86.7%	$6.00
Median output, per 1M	$14.00	$15.00 +7.1%
Lowest unit price	—	$0.001 / request
Cost of 1M in + 200k out	$3.64 +86.7%	$1.95
Context	400K +61.9%	1.1M
Max output	128K	128K
Providers	22 +33.3%	33
Regions	GLOBAL, US	EU, GLOBAL, US
Accepts	application/pdf, 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	image, text
Type	Text models	Text models
Free option	no	no
Cheapest provider	cometapi	xpersona

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, digitalocean, edenai, fastrouter, freemodel, github-copilot, impossibl, jiekou, kilo, ofox, openai, opencode, openrouter, orcarouter, poe, requesty, vercel, zenmux

Frequently asked questions

Which is cheaper, GPT-5.3 Codex or GPT-5.4?

GPT-5.4 is 46% cheaper than GPT-5.3 Codex on input price. GPT-5.4 is 46% cheaper than GPT-5.3 Codex on output price. GPT-5.4 is 46% cheaper than GPT-5.3 Codex on a 1M-in / 200k-out workload.

Which has the larger context, GPT-5.3 Codex or GPT-5.4?

GPT-5.3 Codex: 400K tokens; GPT-5.4: 1.1M tokens.

Where can I use both GPT-5.3 Codex and GPT-5.4?