Modex
ModelsBenchmarksCompareRankingsAgent ToolsBlog
Built on public AI model data.
MethodologyAgent Tools
Created byDiego Gómez González
Models/Microsoft/Microsoft: Phi 4

Microsoft: Phi 4

M

Microsoft

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

+ Compare

Pricing

Source-reported prices are shown in their native units. No missing fee is estimated.

Input

$0.070

USD / 1M input tokens

Output

$0.140

USD / 1M output tokens

Capabilities

A check means the source explicitly lists support; a dash means the source did not publish a value.

Text input Supported
Text output Supported
Vision Not listed
Tools Not listed
Reasoning Not listed
Structured outputs Supported
Audio Not listed
Image generation Not listed
Embeddings Not listed

Alternatives

Suggestions use deterministic rules: overlapping modalities, a context window within 2×, and shared source-reported signals. No AI-generated recommendations.

Similar models

M

Mistral: Mistral Small 3

mistralai/mistral-small-24b-instruct-2501

Input

$0.050

Intelligence

6.7

Similar category, context, price or shared benchmark signals.

A

Amazon: Nova Lite 1.0

amazon/nova-lite-v1

Input

$0.060

Intelligence

6.7

Similar category, context, price or shared benchmark signals.

G

Google: Gemma 3 27B

google/gemma-3-27b-it

Input

$0.080

Intelligence

4.9

Similar category, context, price or shared benchmark signals.

I

Inception: Mercury 2.5

inception/mercury-2.5

Input

$0.040

Intelligence

12.3

Similar category, context, price or shared benchmark signals.

Cheaper alternatives

Strictly lower or equal input and output pricing, with no lower shared benchmark value and similar context.

M

Mistral: Mistral Small 3

mistralai/mistral-small-24b-instruct-2501

Input

$0.050

Intelligence

6.7

Lower source-reported input and output cost while matching or exceeding shared benchmarks.

Higher-performance alternatives

Higher on at least one shared benchmark and never lower on the other shared benchmarks, with similar context.

M

Mistral: Mistral Small 3

mistralai/mistral-small-24b-instruct-2501

Input

$0.050

Intelligence

6.7

Higher source-reported performance on shared benchmark dimensions.

Q

Qwen2.5 Coder 32B Instruct

qwen/qwen-2.5-coder-32b-instruct

Input

$0.660

Intelligence

6.7

Higher source-reported performance on shared benchmark dimensions.

M

Mistral: Saba

mistralai/mistral-saba

Input

$0.200

Intelligence

6.5

Higher source-reported performance on shared benchmark dimensions.