Phi 4
Provider：Microsoft
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Key specs
- Context：16.4K
- Max output：14.7K
- Tokenizer：Other
- Released：2025-01-10
Token pricing
- Input price：$0.070 / 1M tokens
- Output price：$0.140 / 1M tokens
- Blended price：$0.087 / 1M tokens
Modalities
Text
Use Cases
- General Chat：Daily Q&A, copy polishing, knowledge retrieval — covers most general scenarios.（≈ $0.0002/call）
- Lightweight Tasks：Text classification, keyword extraction, sentiment analysis and other high-frequency low-latency tasks.（≈ $0.0001/call）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Low input + output price: solid fit for high-frequency calls and batch processing.
- Low blended price: budget-friendly for fleet-scale deployment.
FAQ
- What is the token pricing of Phi 4? Input price $0.070 / 1M tokens, output price $0.140 / 1M tokens, blended about $0.087 / 1M tokens. Refer to Microsoft’s official page for the exact rate.
- What context window does Phi 4 support? Context window is 16.4K, max output about 14.7K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Phi 4 best for? Based on its capability and pricing, Phi 4 fits best: General Chat, Lightweight Tasks. See the Use Cases section for details and cost estimates.
- What input/output modalities does Phi 4 support? Supports Text modality.
- Is Phi 4 a free model? Phi 4 is billed per token, not a free model.
- Which provider offers Phi 4? Phi 4 is offered by Microsoft.
More models from Microsoft
Full info：Phi 4