Phi 4 reasoning
Microsoft Research 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
Capabilities
Context Window 16k tokens
Max Output 16k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.07
Output $0.14
Cache Read -
Cache Write -
Supported Parameters
frequency_penaltylogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_logprobstop_p