LLM Reference
NVIDIA NIM

Phi-4 Mini Flash Reasoning on NVIDIA NIM

Phi-4 · Microsoft Research

Serverless

Pricing

TypePrice (per 1M)
Input tokensFree
Output tokensFree

Capabilities

VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution

About Phi-4 Mini Flash Reasoning

Lightweight reasoning variant of Microsoft Phi-4 Mini optimized for fast inference.

Get Started

Model Specs

Released2025-12-01
Context128K
ArchitectureDecoder Only

Related Models on NVIDIA NIM