Phi-3 Mini Instruct is Microsoft's language model with a 131K context window and up to 4K output tokens, available from 2 providers, starting at $0.100 / 1M input and $0.100 / 1M output. An instruction-tuned compact Phi-3 Mini model supporting long-context windows for efficient reasoning and chat applications.
Specifications
Canonical IDmicrosoft-phi-3-mini-instruct
TypeLanguage
StatusActive
CreatorMicrosoftMicrosoft
Providers
Context Window131K tokens
Max Output4K tokens
Input ModalitiesText
Output ModalitiesText

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
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

View Azure AI Foundry

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Phi-4 Mini Instruct131K$0.075$0.300Available
Phi-4 MiniAvailable
Phi-4 Mini MMAvailable
Phi-4 Mini Reasoning131K$0.080$0.320Available
Phi-3 Mini Instruct131K$0.100$0.100Current
Phi-3 MiniAvailable
Phi-3.5 Mini Instruct128K$0.130$0.520Available

Other models

ModelTierReleasedContextInput / 1MOutput / 1M
Phi-416K$0.065$0.140
Phi-4 Multimodal
Phi-4 Eagle
Phi-4 Multimodal Instruct131K$0.080$0.320
Phi-4 Reasoning33K$0.125$0.500
Phi-4 Reasoning Plus
Phi-3
Phi-3 Vision Instruct32K$0.200$0.200
Phi-3 Medium InstructMedium128K$0.170$0.680
Phi-3 Small InstructSmall128K$0.150$0.600

Model IDs