Back to Models

Phi-4 Mini

![Microsoft](https://artificialanalysis.ai/img/logos/microsoft_small.svg)Microsoft
8/ 57

Intelligence Score

Intelligence

8

#195 of 212 (top 92%)

Speed

43 tok/s

#125 of 141

Price

Free

per M tokens

Context Window

128K

tokens

Latency: 1ms (#25)

Score Breakdown

Quality Score13%
Speed Score5%
Cost Score100%

Similar Models

Exaone 4.0 1.2B

![LG AI Research](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Flg_small.png&w=32&q=75)LG AI Research

8intelligence

Exaone 4.0 1.2B

![LG AI Research](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Flg_small.png&w=32&q=75)LG AI Research

8intelligence

LFM2.5-1.2B-Thinking

![Liquid AI](https://artificialanalysis.ai/img/logos/liquidai_small.svg)Liquid AI

8intelligence

Jamba 1.7 Mini

![AI21 Labs](https://artificialanalysis.ai/img/logos/ai21_small.svg)AI21 Labs

8intelligence

LFM2.5-1.2B-Instruct

![Liquid AI](https://artificialanalysis.ai/img/logos/liquidai_small.svg)Liquid AI

8intelligence

Use This Model

Claude Code

claude --model phi-4-mini

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "phi-4-mini",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("phi-4-mini"),
  prompt: "Hello",
});
Back to Models