Claude Haiku 4.5 (latest) vs Ministral 3B: API price and specs

Ministral 3B is 92% cheaper than Claude Haiku 4.5 (latest) on input price.

Ministral 3B is 98% cheaper than Claude Haiku 4.5 (latest) on output price.

Ministral 3B is 95% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.

Claude Haiku 4.5 (latest) has a 52.6% larger context than Ministral 3B.

Field	Claude Haiku 4.5 (latest)	Ministral 3B
Lowest input, per 1M	$0.50 +1150%	$0.04
Median input, per 1M	$1.00 +900%	$0.10
Lowest output, per 1M	$2.50 +6150%	$0.04
Median output, per 1M	$5.00 +4900%	$0.10
Lowest unit price	$0.001 / request	—
Cost of 1M in + 200k out	$1.00 +1983.3%	$0.048
Context	200K	131K +34.5%
Max output	64K	8K +87.2%
Providers	34	3 +91.2%
Regions	APAC, AU, EU, GLOBAL, IN, JP, US	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	openrouter	azure

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

azure, edenai, vercel

Frequently asked questions

Which is cheaper, Claude Haiku 4.5 (latest) or Ministral 3B?

Ministral 3B is 92% cheaper than Claude Haiku 4.5 (latest) on input price. Ministral 3B is 98% cheaper than Claude Haiku 4.5 (latest) on output price. Ministral 3B is 95% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.

Which has the larger context, Claude Haiku 4.5 (latest) or Ministral 3B?

Claude Haiku 4.5 (latest): 200K tokens; Ministral 3B: 131K tokens.

Where can I use both Claude Haiku 4.5 (latest) and Ministral 3B?

azure, edenai, vercel