Identity
- Status
- active
- Developer ID
microsoft/Phi-4-multimodal-instruct- Released
- Feb 26, 2025
- Version
- Phi-4-multimodal-instruct
- License
- mit
MicrosoftPhi-4 Multimodal Instruct
Phi-4-multimodal-instruct is an open-weight multimodal language model published by Microsoft.
- Token context
- 131K tokens
- Inputs
- Text, Image, Audio
- Outputs
- Text
- Released
- Feb 26, 2025
Providers & Pricing
0 current hosted offerings
No Current Hosted API Offering Verified
No exact current provider endpoint or published price has been verified for this model version.
At a Glance
Model Facts
Capacity
- Token context
- 131K tokens
- Maximum output
- Unknown
- Total parameters
- 5.6B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text, Image, Audio
- Outputs
- Text
- API available
- Unknown
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- No
- Vision
- Yes
- Tool calling
- No
- Capabilities
- chat, generation
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesmicrosoft/Phi-4-multimodal-instruct, microsoft/Phi-4-multimodal-instruct
Explicit Unknowns
- Maximum output
- Knowledge cutoff
- API availability
- Provider pricing
Primary Evidence
Sources and Observation Date
microsoft/Phi-4-multimodal-instruct developer model repositoryMicrosoft · observed Aug 28, 2026microsoft/Phi-4-multimodal-instruct config.json at 93f923e1a772Microsoft · observed Aug 28, 2026microsoft/Phi-4-multimodal-instruct README.md at 93f923e1a772Microsoft · observed Aug 28, 2026microsoft/Phi-4-multimodal-instruct immutable Hub API metadataMicrosoft · observed Aug 28, 2026Empowering innovation: The next generation of the Phi familyMicrosoft · observed Aug 28, 2026microsoft/Phi-4-multimodal-instruct tokenizer_config.json at 93f923e1a772Microsoft · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Phi-4 Multimodal InstructMicrosoft | vs | Phi-4 ReasoningMicrosoft | family variantstext |
Phi-4 Multimodal InstructMicrosoft | vs |  Molmo2 8BAi2 | cross-developer peersimage, text |
Phi-4 Multimodal InstructMicrosoft | vs |  Lyria 3.5Google DeepMind | cross-developer peersaudio, image, text |
Phi-4 Multimodal InstructMicrosoft | vs | phi-4Microsoft | family variantstext |
Phi-4 Multimodal InstructMicrosoft | vs | Phi-4 Mini InstructMicrosoft | family variantstext |
Phi-4 Multimodal InstructMicrosoft | vs | Phi-4 Mini ReasoningMicrosoft | family variantstext |
Phi-4 Multimodal InstructMicrosoft | vs | VibeVoice ASR Streaming 1.5BMicrosoft | developer peersaudio, text |
Phi-4 Multimodal InstructMicrosoft | vs | VibeVoice ASR Streaming 7BMicrosoft | developer peersaudio, text |
Questions
Phi-4 Multimodal Instruct FAQs
What is Phi-4 Multimodal Instruct?+
Phi-4-multimodal-instruct is an open-weight multimodal language model published by Microsoft. It is developed by Microsoft and its current sourced lifecycle status is active.
What inputs and outputs does Phi-4 Multimodal Instruct support?+
Phi-4 Multimodal Instruct's current record lists Text, Image, and Audio as input and Text as output.
How much context does Phi-4 Multimodal Instruct support?+
The current record lists a 131K-token context window and does not report a maximum output length.
Is Phi-4 Multimodal Instruct available through an API?+
Phi-4 Multimodal Instruct's current primary-source record does not establish API availability. No provider endpoint is treated as available without direct provider evidence.
How large is Phi-4 Multimodal Instruct?+
The current record lists 5.6B total parameters and an unknown active parameter count. Its architecture is Phi4MMForCausalLM.
What capabilities and tasks does Phi-4 Multimodal Instruct support?+
Phi-4 Multimodal Instruct's recorded capabilities are chat and generation. Its supported tasks are audio, image, and text.
How much does Phi-4 Multimodal Instruct cost through an API?+
No directly sourced token price is currently attached to Phi-4 Multimodal Instruct. Missing prices remain unknown rather than being inferred from another model or provider.
Can Phi-4 Multimodal Instruct be self-hosted?+
Phi-4 Multimodal Instruct is an open-weight model. Self-hosting is supported, and the recorded license is mit.
Does Phi-4 Multimodal Instruct have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are microsoft/Phi-4-multimodal-instruct.
Which models can Phi-4 Multimodal Instruct be compared with?+
The current compatible peer set includes Phi-4 Reasoning, Molmo2 8B, Lyria 3.5, phi-4, and Phi-4 Mini Instruct. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →