Provider · Founded 1975 · Redmond, USA

Microsoft: models, pricing and benchmarks

Software company behind the Phi models.

Models

in this index

Avg input

$2.04

per 1M tokens

Avg output

$9.46

per 1M tokens

Open weights

models

Best model

phi-4

by average score

Website

Visit

https://microsoft.com

All Microsoft models

Sorted by average benchmark score. Prices are per million tokens and context is measured in tokens.

#	Model	Provider	Context	Input / 1M	Avg score
1	Phi-4	Microsoft	200000	$3.96	75.4
2	Phi-4 Instruct	Microsoft	128000	$3.79	75.3
3	Phi-4 Chat	Microsoft	65536	$3.66	74.7
4	Phi-4 Base	Microsoft	32768	$3.15	71.2
5	Phi-3.5	Microsoft	16384	$2.81	70.9
6	Phi-3.5 Instruct	Microsoft	16384	$2.67	70.1
7	Phi-3.5 Chat	Microsoft	16384	$2.64	69.0
8	Phi-3.5 Base	Microsoft	65536	$2.24	66.6
9	Phi-4 7B	Microsoft	8192	$0.91	56.8
10	Phi-4 8B	Microsoft	32768	$0.96	54.9
11	Phi-3.5 8B	Microsoft	16384	$0.59	51.2
12	Phi-3.5 7B	Microsoft	4096	$0.50	50.5
13	Phi-4 1.5B	Microsoft	8192	$0.42	48.1
14	Phi-3.5 1.5B	Microsoft	32768	$0.25	44.5

Best Microsoft models

multimodal

Phi-4

Phi-4 is a multimodal model from Microsoft. It offers a 200,000-token context window, costs $3.96 per million input tokens and $20.63 per million output tokens, and averages 75.4 across the index's benchmark suite.

$3.96 in · 200,000 context · 75.4 avg multimodal

Phi-4 Instruct

Phi-4 Instruct is a multimodal model from Microsoft. It offers a 128,000-token context window, costs $3.79 per million input tokens and $17.11 per million output tokens, and averages 75.3 across the index's benchmark suite.

$3.79 in · 128,000 context · 75.3 avg multimodal

Phi-4 Chat

Phi-4 Chat is a multimodal model from Microsoft. It offers a 65,536-token context window, costs $3.66 per million input tokens and $14.24 per million output tokens, and averages 74.7 across the index's benchmark suite.

$3.66 in · 65,536 context · 74.7 avg open-weight

Phi-4 Base

Phi-4 Base is a open-weight model from Microsoft. It offers a 32,768-token context window, costs $3.15 per million input tokens and $11.39 per million output tokens, and averages 71.2 across the index's benchmark suite.

$3.15 in · 32,768 context · 71.2 avg open-weight

Phi-3.5

Phi-3.5 is a open-weight model from Microsoft. It offers a 16,384-token context window, costs $2.81 per million input tokens and $14.99 per million output tokens, and averages 70.9 across the index's benchmark suite.

$2.81 in · 16,384 context · 70.9 avg

How Microsoft fits

Microsoft has 14 models in the index, of which 14 are open weights. The average input price across the lineup is $2.04 per million tokens, and the average output price is $9.46 per million tokens. The strongest model by average benchmark score is phi-4.

Use the table above to compare individual models, or open a model page for its full benchmark breakdown. If you are choosing between providers, start with the comparison pages and then check context limits and licence terms.

FAQ

How many Microsoft models are in the index?

Microsoft has 14 models in this index, of which 14 are open weights.

What is the cheapest Microsoft model?

Phi-3.5 1.5B is the cheapest Microsoft model by input price at $0.25 per million tokens.

What is the best Microsoft model?

Phi-4 has the highest average benchmark score in the Microsoft lineup at 75.4.

Are Microsoft models open weights?

14 of the 14 Microsoft models in this index are open weights. The rest are proprietary.

Where is Microsoft based?

Microsoft was founded in 1975 and is headquartered in Redmond, USA.