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 Microsoft |
|---|---|
| Summary | A compact Microsoft model designed for strong reasoning and math relative to its size. |
| Best for | Private assistants, math, reasoning, efficient self-hosted applications |
| Watch out for | Shorter context and lower broad knowledge than larger frontier models. |
| Family | Phi-4 |
| Type | General LLM |
| Status | GA / open weights |
| Released | 2024-12-12 |
| Context window | 16.4K |
| Max output | 16.4K |
| Inputs | Text |
| Outputs | Text |
| Reasoning | Strong general reasoning |
| 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 |