Phi-4 Mini by Microsoft demonstrates fast output speed, competitive pricing. View detailed benchmark data including scores across coding, math, reasoning, speed, and cost metrics.
Specifications last checked against the provider on . Benchmark scores carry their own source, linked beside each number.
Speed Benchmarks
Cost Benchmarks
Context Benchmarks
Available from 4 providers
The same model costs different amounts depending on who serves it. You can bring your own key for 1 of these — connect it here.
| Provider | Input / 1M | Output / 1M | Cached in | Context | Your key |
|---|---|---|---|---|---|
| Nvidia | $0 | $0 | — | 131K | — |
| Azure | $0.075 | $0.3 | — | 128K | Supported |
| Azure Cognitive Services | $0.075 | $0.3 | — | 128K | — |
| NanoGPT | $0.17 | $0.68 | $0.085 | 128K | — |
Phi-4 Mini — Frequently Asked Questions
How much does Phi-4 Mini cost?
Phi-4 Mini costs $0.00 per 1M input tokens and $0.00 per 1M output tokens. This makes it one of the more affordable models.
How fast is Phi-4 Mini?
Phi-4 Mini generates output at 150 tokens per second, which is very fast compared to other models.
What is the context window of Phi-4 Mini?
Phi-4 Mini has a context window of 131K tokens. This determines how much text, conversation history, and code the model can process in a single request.
Who created Phi-4 Mini?
Phi-4 Mini was created by Microsoft. It is classified as a open source model in our catalogue.
Is Phi-4 Mini open source?
Yes, Phi-4 Mini is an open-source model. The model weights are publicly available for download and self-hosting.