Using Phi 4 Multimodal Instruct on NVIDIA NIM

Implementation guide · Phi-4 · Microsoft Research

ServerlessOpen Source

NVIDIA NIM exposes Phi 4 Multimodal Instruct through model ID microsoft/phi-4-multimodal-instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-05-22. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call microsoft/phi-4-multimodal-instruct — see the documentation for request format.
  3. 3
    You'll be billed . See full pricing.
API PortalDocumentationPricing

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

Capabilities

VisionMultimodal

About Phi 4 Multimodal Instruct

Phi 4 Multimodal Instruct is Microsoft Research's Phi-4 model focused on multimodal input across text, image, and beyond. It offers a 128K-token context window with weights openly available for self-hosting.

Full model details →

Model Specs

Released2025-01-01
Parameters5.6B
Context128k
ArchitectureDecoder Only
Knowledge cutoff2024-06

More Models on NVIDIA NIM

Phi-4 MiniPhi-4 Mini Flash Reasoning
All models on NVIDIA NIM →

Also available on(2)

Fireworks AI$0.90/1MMicrosoft Foundry
Compare all providers →

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States