Phi-4-Mini by Nvidia | AI model information

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

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

Jul 16, 2026, 7:00 PMUTC

Nations have always invested in critical infrastructure to grow their economies and improve citizens’ lives, from transportation and communications to commerce, entertainment and healthcare. Today, AI is the most important layer of that infrastructure. It is turbocharging…

Jul 16, 2026, 12:05 AMUTC

Jensen. @SEGA. Akihabara. 🎮 Some collabs are just meant to be. We stepped into the heart of Tokyo's most legendary gaming district to celebrate decades of shared history, and the next era with @NVIDIARTXSpark. Video

Jul 15, 2026, 11:49 PMUTC

Read the blog: nvda.ws/4hgaxW1 Link NVIDIA and Japan Bring Full-Stack AI and Robotics to Every Industry NVIDIA and its partners in Japan are this week showcasing the AI ecosystem's latest advancements. Check back here for updates. blogs.nvidia.com

Jul 15, 2026, 11:49 PMUTC

Japan's biggest banks spent the last few years evaluating AI. Now they're building the infrastructure for it. 🏭 We're working with Mizuho, SMFG, Rakuten Bank, and MUFG NICOS to build the AI factories making that possible — using NVIDIA Nemotron open models and Agent Toolkit…

Jul 15, 2026, 11:47 PMUTC

Building a production-ready vision AI agent no longer takes thousands of developer hours. NVIDIA Metropolis offers 80+ open agent skills for generating synthetic data, fine-tuning models, deploying applications and unlocking real-time insights, all through natural-language…