AIModelsTester
Microsofttext->text

Microsoft: Phi 4

[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 parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs. For more information, please see [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)

Context Window

16K

Input Price

$0.0600/M tokens

Output Price

$0.1400/M tokens

Modality

text->text

Pricing Breakdown
Cost per million tokens for input and output
Input$0.0600/M tokens
Output$0.1400/M tokens

Cost Example: Processing 10,000 input tokens and generating 1,000 output tokens would cost approximately $0.000740

Context Window Size
Maximum tokens the model can process in a single request
Context Window16K tokens
2% of 1M max

~12K

Words Equivalent

~8

Pages of Text

~164

Code Functions

Best Use Cases
What this model excels at
MathReasoningAnalysisData-analysisAnalyticsResearchAcademic

Related Categories:

Ready to Test Microsoft: Phi 4?

Use our free AI Models Tester to compare Microsoft: Phi 4 with other models side-by-side using your own prompts. See real results instantly.