GitHub Models

Phi-4-multimodal-instruct

Name: Phi-4-multimodal-instruct
Brand: GitHub Models

Canonical ID: github_models/microsoft/phi-4-multimodal-instruct

More GitHub Models models More phi-4-multimodal-instruct family models

Phi-4-multimodal-instruct is listed under GitHub Models in LLM Directory with pricing, context limits, modalities, and capability metadata for quick comparison.

Reasoning: Yes Tool use: Yes

Overview

text image audio

Provider: GitHub Models
Family: phi-4-multimodal-instruct
Release date: 2024-12-11
Last updated: 2024-12-11
Input modalities: text, image, audio
Output modalities: text

Pricing and Limits

Token pricing

Input: $0/1M
Output: $0/1M
Cached input: N/A

Context and output

Context window: 128,000
Max output tokens: 4,096
Qualified ID: github_models/microsoft/phi-4-multimodal-instruct

Model Summary

Phi-4-multimodal-instruct is a model listing in the GitHub Models provider catalog. It is categorized under the phi-4-multimodal-instruct family.

The model supports text, image, audio modalities across input/output paths. Reported context capacity is 128,000. Pricing is listed at $0/1M input and $0/1M output.

Same Family: phi-4-multimodal-instruct

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Phi-4 15B evroc/microsoft/Phi-4-multimodal-instruct	evroc	32,000	$0.24/1M	$0.47/1M
Phi 4 Multimodal nvidia/microsoft/phi-4-multimodal-instruct	Nvidia	128,000	$0/1M	$0/1M

Phi-4-multimodal-instruct

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From GitHub Models

AI21 Jamba 1.5 Large

AI21 Jamba 1.5 Mini

Codestral 25.01

Cohere Command A

Cohere Command R

Cohere Command R+

Cohere Command R 08-2024

Cohere Command R+ 08-2024

Same Family: phi-4-multimodal-instruct