Claude Haiku 5.5 vs Ministral 3 14B 2512: API price and specs

Claude Haiku 5.5 is 75% cheaper than Ministral 3 14B 2512 on input price.

Ministral 3 14B 2512 is 20% cheaper than Claude Haiku 5.5 on output price.

Claude Haiku 5.5 is 58% cheaper than Ministral 3 14B 2512 on a 1M-in / 200k-out workload.

Claude Haiku 5.5 has a 281.5% larger context than Ministral 3 14B 2512.

Field	Claude Haiku 5.5	Ministral 3 14B 2512
Lowest input, per 1M	$0.05	$0.20 +300%
Median input, per 1M	$0.10	$0.22 +115.5%
Lowest output, per 1M	$0.25 +25%	$0.20
Median output, per 1M	$0.50 +132%	$0.22
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.10	$0.24 +140%
Context	1M	262K +73.8%
Max output	128K +50%	256K
Providers	33	7 +78.8%
Regions	AU, EU, GLOBAL, JP, US	EU, GLOBAL
Accepts	application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text	image, text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	iteracompute	edenai

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

302ai, aiml, cortecs, edenai, kilo, openrouter, trustedrouter

Frequently asked questions

Which is cheaper, Claude Haiku 5.5 or Ministral 3 14B 2512?

Claude Haiku 5.5 is 75% cheaper than Ministral 3 14B 2512 on input price. Ministral 3 14B 2512 is 20% cheaper than Claude Haiku 5.5 on output price. Claude Haiku 5.5 is 58% cheaper than Ministral 3 14B 2512 on a 1M-in / 200k-out workload.

Which has the larger context, Claude Haiku 5.5 or Ministral 3 14B 2512?

Claude Haiku 5.5: 1M tokens; Ministral 3 14B 2512: 262K tokens.

Where can I use both Claude Haiku 5.5 and Ministral 3 14B 2512?

302ai, aiml, cortecs, edenai, kilo, openrouter, trustedrouter