Phi 4

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.

Try Now

Example Use Cases

Efficient complex reasoning

Lightweight microsoft model

Resource-constrained reasoning task

Technical Specifications

Context Window

16,384 tokens

Max Output

16,384 tokens

Cache Miss Cost

$0.06 per 1M tokens

Non-Reasoning Cost

$0.14 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls

⚠️ Legacy

Made legacy on

Reason

Untested

Recommended Replacement

Qwen3.5 Plus