Phi-4-Mini by Nvidia | AI model information

$10 off Synthetic - fastest OpenCode provider$10 off Synthetic - the fastest Kimi K2.6 and GLM 5.1 provider Discuss

Model details

Phi-4-Mini

Nvidiamicrosoft/phi-4-mini-instructphi

Open provider page Provider docs

Quick Info

Provider: Nvidia
Model key: microsoft/phi-4-mini-instruct
Release date: Dec 1, 2024
Last updated: Sep 5, 2025

Cost

A provider subscription or plan supersedes token-based pricing for this model.

Limits

Output tokens: 8,192 tokens
Context window: 131,072 tokens

Latest news about Phi-4-Mini

No articles yet. Fetch the latest news to show it here.

Videos about Phi-4-Mini

Recent tweets and retweets from Nvidia

Jun 2, 2026, 11:50 PMUTC

Some of the best conversations happen over great food. 🍧 @lexfridman + Jensen + night markets = one of the best evenings in Taipei.

Jun 2, 2026, 11:33 PMUTC

The energy at GTC Taipei is unmatched. 💚 From packed sessions and live demos to conversations shaping what’s next in AI, here’s a look at the action across a show floor where innovation comes to life. Video

Jun 2, 2026, 9:04 PMUTC

Taiwan isn’t just building AI infrastructure, it’s powering the world’s AI factory buildout. 👏 From fabs to factory floors, leaders like TSMC, Foxconn, QCT, Pegatron, and Wistron are using accelerated computing, digital twins, and AI agents to transform how AI systems are…

Jun 2, 2026, 8:28 PMUTC

What does it take to build an AI factory ready for the agentic era? 80+ partners joined Jensen Huang at #NVIDIAGTC Taipei to show how NVIDIA MGX is making it possible. With NVIDIA Vera Rubin, 800 VDC, and partners spanning systems, power, and cooling, NVIDIA MGX is turning…

Jun 2, 2026, 8:15 PMUTC

NVIDIA DGX Station systems are beginning to arrive at the desks of developers and researchers. 📦 Enterprise teams can deploy data center-level performance locally with GB300-powered systems arriving from partners like @ASUS, @Dell, @GIGABYTEUSA, @HP, MSI and @Supermicro. 👉…