Microsoft · Phi 4 Reasoning · active
Phi-4-reasoning
Phi-4-reasoning is an open-weight language model published by Microsoft.
microsoft/Phi-4-reasoningProvider availability
Serving endpoints and pricing
This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.
Technical specification
Capabilities
Version lineage
Explicit unknowns
- Maximum output
- Knowledge cutoff
- API availability
- Provider pricing
Comparable peers
Related model comparisons
Questions
Phi-4-reasoning FAQs
What is Phi-4-reasoning?+
Phi-4-reasoning is an open-weight 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-reasoning support?+
Phi-4-reasoning's current record lists Text as input and Text as output.
How much context does Phi-4-reasoning support?+
The current record lists a 32,768-token context window and does not report a maximum output length.
Is Phi-4-reasoning available through an API?+
Phi-4-reasoning'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-reasoning?+
The current record lists 14.7B total parameters and an unknown active parameter count. Its architecture is Phi3ForCausalLM.
What capabilities and tasks does Phi-4-reasoning support?+
Phi-4-reasoning's recorded capabilities are chat, generation, and reasoning. Its supported tasks are text.
Can Phi-4-reasoning be self-hosted?+
Phi-4-reasoning is an open-weight model. Self-hosting is supported, and the recorded license is mit.
Does Phi-4-reasoning have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are microsoft/Phi-4-reasoning.
Which models can Phi-4-reasoning be compared with?+
The current compatible peer set includes Phi-4-mini-reasoning, phi-4, Phi-4-multimodal-instruct, Phi-4-mini-instruct, and Olmo-3-7B-Think. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →
How current is the Model Markets record for Phi-4-reasoning?+
Phi-4-reasoning was last verified Aug 28, 2026 from Microsoft's primary source, “microsoft/Phi-4-reasoning developer model repository.” The evidence is classified as official fact.
Primary evidence