Phi-3.5-mini-instruct — Free API

What is Phi-3.5-mini-instruct?

Phi-3.5 Mini Instruct is Microsoft's efficient 3.8B open model, available free on Hugging Face's Serverless Inference API. Despite its small size, it delivers surprisingly strong reasoning and instruction-following for lightweight tasks, with a 128K context window that belies its compact footprint. Ideal for resource-constrained applications, simple Q&A, and as a baseline for model evaluation. Uses Hugging Face's native API format; approximately 1,000 requests per day on the free tier. Registration required.

Phi-3.5-mini-instruct API Code Example

Paste your API key and run. See the config generator for Claude Code, Cursor, and more tools.

from openai import OpenAI

client = OpenAI(
    base_url="https://router.huggingface.co/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="phi-3-5-mini-instruct",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://router.huggingface.co/v1",
  apiKey: "YOUR_API_KEY",
});

const completion = await openai.chat.completions.create({
  model: "phi-3-5-mini-instruct",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(completion.choices[0].message.content);

curl https://router.huggingface.co/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "phi-3-5-mini-instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Other Free Models from Hugging Face