Microsoft model product
Phi 4 Mini Reasoning
Phi 4 Mini Reasoning is an LLM from Microsoft designed for multi-step mathematical and logic-intensive problem solving in memory- and compute-constrained, latency-bound environments.
Updated Sep 8, 2026. Default version: Phi 4 Mini Reasoning
LLMBoard Score12.2Phi 4 Mini Reasoning
Coverage0%2 benchmark families
Context windowN/ATokens
Official input price$0.075Azure API
Phi 4 Mini Reasoning Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Phi 4 Mini Reasoning Benchmark Results
Benchmark scores for Phi 4 Mini Reasoning.
Sort by
Phi 4 Mini Reasoning Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Phi 4 Mini Reasoning Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.075 input, $0.30 output per 1M
- Official provider
- Azure
- Lowest third-party
- From $0.075 input, $0.30 output per 1M via Azure Cognitive Services
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderAzure Cognitive Services | Provider model IDphi-4-mini-reasoning | Regionglobal | Input / 1M$0.075 | Output / 1M$0.30 | Context128K | Updated |
| ProviderAzure | Provider model IDphi-4-mini-reasoning | Regionglobal | Input / 1M$0.075 | Output / 1M$0.30 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Phi 4 Mini Reasoning Runtime Performance
Provider-specific output speed and catalog latency for Phi 4 Mini Reasoning. Runtime does not affect the capability score.
No runtime data
No provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Phi 4 Mini Reasoning Specifications
Technical details for the model's default version.
- Version
- Phi 4 Mini Reasoning
- Released
- Apr 30, 2025
- Knowledge cutoff
- Feb 1, 2025
- Parameters
- 3.8B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- Yes
- License
- MIT
Phi 4 Mini Reasoning Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionPhi 4 Mini Reasoning | Released | LLMBoard12.20 | Parameters3.8B | ContextN/A | Max outputN/A | Open weightsYes | LicenseMIT |
Models similar to Phi 4 Mini Reasoning
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MI
Phi 4
Microsoft
MI
Phi 4 multimodal
Microsoft
MI
Phi 3.5 MoE
Microsoft
MI
Phi 4 Reasoning
Microsoft
MI
Phi 3.5 mini
Microsoft
MI
Phi 3.5 vision
Microsoft
What is Phi 4 Mini Reasoning?
Key information about Phi 4 Mini Reasoning and its available data.
Phi 4 Mini Reasoning is a Microsoft LLM for formal proof generation, symbolic computation, advanced word problems, and other mathematical reasoning tasks. It is designed to maintain context across steps and apply structured logic.
Data as of 2026-09-08.
FAQ
Common questions about Phi 4 Mini Reasoning.
When was Phi 4 Mini Reasoning released?
Phi 4 Mini Reasoning's default version was released on Apr 30, 2025.
How much does Phi 4 Mini Reasoning cost?
Phi 4 Mini Reasoning's official API price is $0.075 per million input tokens and $0.30 per million output tokens via Azure. The lowest tracked third-party offer starts at $0.075 input and $0.30 output via Azure Cognitive Services.
Who created Phi 4 Mini Reasoning?
Phi 4 Mini Reasoning was created by Microsoft.
What is the context window for Phi 4 Mini Reasoning?
A context window is not available for the default version.
Is Phi 4 Mini Reasoning open weight?
Yes. The default version is marked as open weight under MIT.