Phi-4 Multimodal Instruct is Microsoft's language model with a 131K context window and up to 4K output tokens, starting at $0.08 / 1M input and $0.32 / 1M output. A multimodal instruction-tuned variant of Phi-4 capable of processing both text and visual inputs for a compact yet capable small language model.
Specifications
Canonical IDmicrosoft-phi-4-multimodal-instruct
TypeLanguage
StatusActive
CreatorMicrosoftMicrosoft
Providers
Context Window131K tokens
Max Output4K tokens
Input ModalitiesAudioImage
Output ModalitiesText

Capabilities

Input2/5
Text·
Image✓
Audio✓
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Audio In
$ / 1M
Azure AI Foundry logo
Azure AI Foundry
azure_ai/Phi-4-multimodal-instruct
$0.08$0.32$4.00

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Phi-4 Mini Instruct131K$0.075$0.300Deprecated
Phi-416K$0.070$0.140Available
Phi-4 Multimodal Instruct—131K$0.080$0.320Current
Phi-4 Mini————Available
Phi-4 Multimodal————Available
Phi-4 Eagle————Available
Phi-4 Mini MM————Available
Phi-4 Mini Reasoning—131K——Available
Phi-4 Reasoning—33K——Available
Phi-4 Reasoning Plus————Available
Phi-3 Mini————Available

Model IDs

azure_ai/Phi-4-multimodal-instruct
microsoft-phi-4-multimodal-instruct