Microsoft: Phi 4

MicrosoftID: 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)

Pricing per 1M Tokens

Input (Prompt)$0.07
Output (Completion)$0.14
Cache ReadFree
Cache WriteFree
ImageN/A

Specifications

Context Length16K
Max Output Tokens16K
Input ModalitiesText
Output ModalitiesText
TokenizerOther
Instruct TypeN/A
Top Provider Context16K
Top Provider Max Output16K
ModeratedNo

Compare this model

See how Microsoft: Phi 4 stacks up against other models.

More from Microsoft

Last updated: March 23, 2026

First tracked: March 23, 2026