Using Phi-4 Mini on Microsoft Foundry

Implementation guide · Phi-4 · Microsoft Research

Serverless
Open Source

Microsoft Foundry exposes Phi-4 Mini through model ID Phi-4-mini-instruct. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-18. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Microsoft Foundry and generate an API key.
  2. 2
    Use the Microsoft Foundry SDK or REST API to call Phi-4-mini-instruct — see the documentation for request format.
  3. 3
    You'll be billed $0.07/1M input, $0.30/1M output tokens. See full pricing.
API PortalDocumentationPricing

Code Examples

See Microsoft Foundry documentation for integration details.

Pricing on Microsoft Foundry

TypePrice (per 1M)
Input tokens$0.07
Output tokens$0.30

Capabilities

No model capability flags are currently sourced.

About Phi-4 Mini

Phi-4 family model from Microsoft Research. Mini variant with efficient performance.

Full model details →

Model Specs

Released2024-12-13
Parameters3.8B
Context128K
Knowledge cutoff2024-06

More Models on Microsoft Foundry

Phi-4 14BPhi 4 Multimodal InstructPhi 4 ReasoningPhi 4 Reasoning Plus
All models on Microsoft Foundry →

Also available on(3)

Novita AI$0.05/1MFireworks AINVIDIA NIM
Compare all providers →

Provider

Microsoft Foundry

Microsoft

Redmond, Washington, United States