Phi 4

About Phi 4

[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)

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

Ministral 3 3B 2512

Mistral

Input: $0.10

Output: $0.10

Context: 131k

Gemma 3 12B

Google

Input: $0.05

Output: $0.15

Context: 131k

Reka Edge

Rekaai

Input: $0.10

Output: $0.10

Context: 16k

Nemotron Nano 9B V2

NVIDIA

Input: $0.04

Output: $0.16

Context: 131k

💡 Cheaper Alternatives

Same Brand (Microsoft)

Cross Brand

🚀 Quick Start

Get started with Phi 4 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",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision