All Models

Phi-4

phi Reasoning Tool Calling Open Weights

[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)

Providers 3
Released Dec 11, 2024
Input Modalities text
Output Modalities text
Tarsk Use coding

Available Providers (3)

Provider Model ID Input Cost Output Cost Context Max Output Docs
GitHub Models microsoft/phi-4 $0.00/MTok $0.00/MTok 16K 4.1K
Azure Cognitive Services phi-4 $0.13/MTok $0.50/MTok 128K 4.1K
Azure phi-4 $0.13/MTok $0.50/MTok 128K 4.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output