checklist.day

Phi-4 Multimodal Instruct

JSON →
microsoft multimodal
textimageaudio

A multimodal instruction-tuned model from Microsoft Phi-4 family capable of processing text, images, and audio.

Specs

context window 131K tokens
max output 4K tokens
input price $0.08 / 1M tokens
output price $0.32 / 1M tokens

Capabilities

visionstreamingreasoningcode-generationfunction-calling

Dates

releasedFeb 2025
knowledge cutoffJun 2024

Resources

homepagehuggingface.co/microsoft/Phi-4-multimodal-instruct ↗

API

full doc /v1/models/microsoft/Phi-4-multimodal-instruct