Claude Haiku 4.5 (latest) vs Phi-4-reasoning-plus: API price and specs

Phi-4-reasoning-plus is 86% cheaper than Claude Haiku 4.5 (latest) on input price.

Phi-4-reasoning-plus is 86% cheaper than Claude Haiku 4.5 (latest) on output price.

Phi-4-reasoning-plus is 86% cheaper than Claude Haiku 4.5 (latest) on a 1M-in / 200k-out workload.

Claude Haiku 4.5 (latest) has a 510.4% larger context than Phi-4-reasoning-plus.

Field	Claude Haiku 4.5 (latest)	Phi-4-reasoning-plus
Lowest input, per 1M	$0.50 +614.3%	$0.07
Median input, per 1M	$1.00 +925.6%	$0.0975
Lowest output, per 1M	$2.50 +614.3%	$0.35
Median output, per 1M	$5.00 +1076.5%	$0.42
Lowest unit price	$0.001 / request	—
Cost of 1M in + 200k out	$1.00 +614.3%	$0.14
Context	200K	33K +83.6%
Max output	64K	4K +93.6%
Providers	34	2 +94.1%
Regions	APAC, AU, EU, GLOBAL, IN, JP, US	—
Accepts	application/pdf, file, image, image/gif, image/jpeg, image/png, image/webp, pdf, text	text
Returns	text	text
Type	Text models	Text models
Free option	no	no
Cheapest provider	openrouter	deepinfra

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, deepinfra

Frequently asked questions

Which is cheaper, Claude Haiku 4.5 (latest) or Phi-4-reasoning-plus?

Phi-4-reasoning-plus is 86% cheaper than Claude Haiku 4.5 (latest) on input price. Phi-4-reasoning-plus is 86% cheaper than Claude Haiku 4.5 (latest) on output price. Phi-4-reasoning-plus is 86% 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 Phi-4-reasoning-plus?

Claude Haiku 4.5 (latest): 200K tokens; Phi-4-reasoning-plus: 33K tokens.

Where can I use both Claude Haiku 4.5 (latest) and Phi-4-reasoning-plus?

azure, deepinfra