---
id: "microsoft/phi-4"
also: ["microsoft/phi-4", "hf/microsoft/phi-4", "requesty/microsoft/phi-4"]
cheapest_list_usd_per_m: "0.056 in, 0.112 out, at deepinfra/bf16/flex on openrouter"
cheapest_effective_usd_per_m: "0.0557 in, 0.1104 out, at deepinfra/bf16/flex on openrouter"
context: 16384
max_output: 14745
input: ["text"]
output: ["text"]
released: "2025-01-10"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p"]
endpoints: 5
gateways: "hf (2), openrouter (2), requesty (1)"
no_training: 3
trains: 0
retains_prompts: 0
---
# Microsoft: Phi 4

Phi-4-reasoning-plus is an enhanced 14B parameter model from Microsoft, fine-tuned from Phi-4 with additional reinforcement learning to boost accuracy on math, science, and code reasoning tasks. It uses the same dense decoder-only transformer architecture as Phi-4, but generates longer, more comprehensive outputs structured into a step-by-step reasoning trace and final answer.

While it offers improved benchmark scores over Phi-4-reasoning across tasks like AIME, OmniMath, and HumanEvalPlus, its responses are typically \~50% longer, resulting in higher latency. Designed for English-only applications, it is well-suited for structured reasoning workflows where output quality takes priority over response speed.