Phi 4 Reasoning Plus

About Phi 4 Reasoning Plus

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.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Microsoft Model Lineup

Compare all models from Microsoft to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Llama 3.3 70B Instruct

Meta

Input: $0.10

Output: $0.32

Context: 131k

DeepSeek V4 Flash 0731

DeepSeek

Input: $0.14

Output: $0.28

Context: 1.0M

DeepSeek V4 Flash 0423

DeepSeek

Input: $0.14

Output: $0.28

Context: 1.0M

MiMo-V2.5

Xiaomi

Input: $0.14

Output: $0.28

Context: 1.1M

💡 Cheaper Alternatives

Same Brand (Microsoft)

Cross Brand

🚀 Quick Start

Get started with Phi 4 Reasoning Plus API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="microsoft/phi-4-reasoning-plus-04-30",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision