Microsoft
Phi-4-reasoning-plus
Microsoft's reinforcement-learning variant of Phi-4-reasoning, released April 30, 2025 with MIT-licensed weights. It retains the 14B dense architecture, text input and output, and 32K-token context. Microsoft reports longer reasoning responses and higher latency than the base reasoning variant, making it useful when additional reasoning time is acceptable.
32K tokens
Text only
Pro
- Provider
- Microsoft
- Context
- 32KCatalog · As of Aug 24, 2026Within 30d
- yno subscription tier
- Pro
- Released
- Apr 30, 2025
- Speed
- Medium
- Reasoning
- Expert
- Modality
- Text only
Benchmarks
Quality
Not available
Speed and latency
Not available
API pricing
Not available
AA measurements unavailable
Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology
Capabilities
- Reasoning
- Small Model
- RL-tuned
- Math
- Code
Use cases
- Hard reasoning at edge
- RL-tuned deployments
- Math/science
- Local agents
Strengths
- Reinforcement-learning tuning
- Longer reasoning responses
- 14B dense parameters
- MIT-licensed weights
Best for
Teams evaluating local reasoning with more time available per response
Use Phi-4-reasoning-plus in yno.ai
No credit card required
Related models
Frequently asked
- What is Phi-4-reasoning-plus?
- Microsoft's reinforcement-learning variant of Phi-4-reasoning, released April 30, 2025 with MIT-licensed weights. It retains the 14B dense architecture, text input and output, and 32K-token context. Microsoft reports longer reasoning responses and higher latency than the base reasoning variant, making it useful when additional reasoning time is acceptable.
- How much does Phi-4-reasoning-plus cost in yno.ai?
- Phi-4-reasoning-plus is available on the Pro tier of yno.ai.
- What can Phi-4-reasoning-plus do?
- Phi-4-reasoning-plus is best for Teams evaluating local reasoning with more time available per response. Its main capabilities include Reasoning, Small Model, RL-tuned, Math, Code.
- How does Phi-4-reasoning-plus compare to other models?
- Phi-4-reasoning-plus excels at Reinforcement-learning tuning and is recommended for Hard reasoning at edge, RL-tuned deployments, Math/science, Local agents. See related models below.
- How do I use Phi-4-reasoning-plus in yno.ai?
- Sign up for yno.ai, select Phi-4-reasoning-plus from the model picker, and start chatting.