What is the cheapest Microsoft model?

Phi 4, at $0.07 per million input tokens and $0.14 per million output tokens.

How much does Phi 4 cost?

$0.07 per million input tokens and $0.14 per million output tokens at list price.

How many Microsoft models are available through the API?

2 are listed on OpenRouter right now, 2 of them paid.

Live · refreshed hourly

Microsoft API pricing

Every Microsoft model available through OpenRouter, at Microsoft's list price per million tokens.

Newest

Phi 4

$0.07 in · $0.14 out

Cheapest

Phi 4

$0.07 in · $0.14 out

Most expensive

WizardLM-2 8x22B

$0.62 in · $0.62 out

All Microsoft models and prices

Model	Input / 1M	Output / 1M	Blended 3:1	Context
Phi 4	$0.07	$0.14	$0.088	16K
WizardLM-2 8x22B	$0.62	$0.62	$0.62	66K

Per million tokens, list price. Newest first.

Where to buy Microsoft API credits for less

Microsoft models cost the same per token wherever they're billed through OpenRouter. The credits don't. Live quotes for $100 of usage:

#	Where you buy	You payYou pay for $100.00 of usage	vs list price	Price source
1	OrbioCardCheapest right now Credits from a discount book, plus a 5% platform fee and card processing, both included in the quote.	$85.10 incl. $2.60 card processing	-14.9%	live quote
2	smaaartCard Credits from a discount book, plus a 5% platform fee on face value. Card processing and taxes shown at checkout.	$95.00 + card processing and tax at checkout (not in this number)	-5.0%	live quote
3	Direct from the labCard Prepaid credits at face value (OpenAI, Anthropic, Google…). Taxes may apply.	$100.00 no top-up fee	list price	face value
4	OpenRouterCrypto 5% on crypto purchases. No markup on model prices.	$105.00 fees included	+5.0%	published fee
5	OpenRouterCard 5.5% on card purchases, $0.80 minimum. No markup on model prices.	$105.50 fees included	+5.5%	published fee

Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare