AI model comparison
Open Cost Calculator
Compare AI models side by side.
Pick up to four models and compare the trade-offs that matter: context, price, API access, weights, inputs, outputs, and use cases.
| Attribute | Phi-4-reasoning Microsoft |
|---|---|
| Summary | A Phi-4 variant tuned specifically for multi-step reasoning in math and complex problem solving. |
| Best for | Math, logic, reasoning research, private analytical assistants |
| Watch out for | Reasoning can be verbose; less suitable for broad multimodal tasks. |
| Family | Phi-4 |
| Type | Reasoning LLM |
| Status | GA / open weights |
| Released | 2025-04-30 |
| Context window | 32.8K |
| Max output | 32.8K |
| Inputs | Text |
| Outputs | Text |
| Reasoning | Yes — specialized |
| Tool calling | Host dependent |
| Structured output | Host dependent |
| API available | Yes and self-hosted |
| Open weights | Yes |
| Self-hostable | Yes |
| License | MIT |
| Price | See provider pricing |