Claude Haiku 5.5 vs GPT-5.1 Codex Max: API price and specs

Claude Haiku 5.5 is 95% cheaper than GPT-5.1 Codex Max on input price.

Claude Haiku 5.5 is 97% cheaper than GPT-5.1 Codex Max on output price.

Claude Haiku 5.5 is 97% cheaper than GPT-5.1 Codex Max on a 1M-in / 200k-out workload.

Claude Haiku 5.5 has a 150% larger context than GPT-5.1 Codex Max.

Field	Claude Haiku 5.5	GPT-5.1 Codex Max
Lowest input, per 1M	$0.05	$1.10 +2100%
Median input, per 1M	$0.10	$1.25 +1150%
Lowest output, per 1M	$0.25	$9.00 +3500%
Median output, per 1M	$0.50	$10.00 +1900%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.10	$2.90 +2800%
Context	1M	400K +60%
Max output	128K	128K
Providers	33	11 +66.7%
Regions	AU, EU, GLOBAL, JP, US	GLOBAL
Accepts	application/pdf, 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	iteracompute	poe

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, aiml, azure, edenai, jiekou, kilo, ofox, opencode, openrouter, poe, vercel

Frequently asked questions

Which is cheaper, Claude Haiku 5.5 or GPT-5.1 Codex Max?

Claude Haiku 5.5 is 95% cheaper than GPT-5.1 Codex Max on input price. Claude Haiku 5.5 is 97% cheaper than GPT-5.1 Codex Max on output price. Claude Haiku 5.5 is 97% cheaper than GPT-5.1 Codex Max on a 1M-in / 200k-out workload.

Which has the larger context, Claude Haiku 5.5 or GPT-5.1 Codex Max?

Claude Haiku 5.5: 1M tokens; GPT-5.1 Codex Max: 400K tokens.

Where can I use both Claude Haiku 5.5 and GPT-5.1 Codex Max?

aihubmix, aiml, azure, edenai, jiekou, kilo, ofox, opencode, openrouter, poe, vercel