Phi

Phi-4-mini-instruct

microsoft/Phi-4-mini-instruct

Create Deployment Open Playground

Overview

Phi-4-Mini is a lightweight open model built upon synthetic and filtered public data, focusing on high-quality, reasoning-dense information. With 3.8 billion parameters and a 128K token context length, it features a dense decoder-only Transformer architecture with updates for efficiency and multilingual support. This instruction-tuned model is suitable for memory/compute constrained environments and latency-bound scenarios while aiming for strong reasoning capabilities, particularly in math and logic.

Tags

CentML Optimized

Chat

Dedicated

LLM

Serverless

API

Select a language: 
curl -X POST "https://api.centml.com/openai/v1/chat/completions" \
  -H "Authorization: Bearer *******************************************" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "microsoft/Phi-4-mini-instruct",
    "messages": [{ "role": "system", "content": "You are a helpful assistant." }],
    "stream": false
  }'
from openai import OpenAI

client = OpenAI(
	api_key="*******************************************",
	base_url="https://api.centml.com/openai/v1"
)

completion = client.chat.completions.create(
    model="microsoft/Phi-4-mini-instruct",
    messages=[{ "role": "system", "content": "You are a helpful assistant." }],
    stream=False,
)

print(completion.choices[0].message)
import OpenAI from "openai";

const client = new OpenAI(
	api_key="*******************************************",
	base_url="https://api.centml.com/openai/v1"
)

async function main() {
  const completion = await client.chat.completions.create({
    model: "microsoft/Phi-4-mini-instruct",
    messages: [{ "role": "system", "content": "You are a helpful assistant." }],
    stream: false,
  });

  console.log(completion.choices[0])
}

main()