Phi 4 Multimodal Instruct

Released
2025-01-01
Last refreshed
2026-05-22
Status
Researched 131d ago
Open sourceCommercial use: permittedMultimodalLong contextVision
Microsoft Research releases · 6 in the last 12 months · this family litChangelog →
Specifications
Family
Phi-4
Released
2025-01-01
Context
128k
Parameters
5.6B
Architecture
Decoder Only
Knowledge cutoff
2024-06
Specialization
multimodal
Openness
Open source
License
MITOSI-approvedCommercial use: permitted
Weights
Unknown
Code
Unknown
Training
Pretrained
Created by

Advancing the state-of-the-art in AI and computing.

Redmond, Washington, United States
Founded 1991
Website
Pricing
Output / 1M
$0.900
Input / 1M
$0.900

Cheapest of 3 routes · Fireworks AI

About

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.

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Fireworks AI$0.900$0.900
Serverless
Microsoft Foundry--
ServerlessPartial
NVIDIA NIM--
ServerlessPartial

Available via routers & gateways(7)

Capabilities

VisionMultimodal

Benchmark peer barsfor Long context

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
MMMU Pro38.5LLM-Stats aggregatorObserved 2026-06-07—Source

Migration checks

No linked migration route is available for this model yet.

Compare Phi 4 Multimodal Instruct with other models