Microsoft: Phi 4
microsoft/phi-4
Input Price
$0.07 / 1M
Output Price
$0.14 / 1M
Context Length
16,384
LLM Price Calculator
Enter custom token counts to calculate exact pricing for your specific AI use case.
- Input Cost
- $0.07
- Output Cost
- $0.14
- Total Cost
- $0.21
About this model
[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...
Try this model in Playground
Test this model's capabilities in different AI playground environments including OpenRouter, Hugging Face, Cloudflare, and Vercel.
FAQ
Microsoft: Phi 4 pricing FAQ
Answers about this model's pricing, context window, supported modalities, and where to try it.
How much does Microsoft: Phi 4 cost?
Use the calculator above to estimate the cost for your expected workload. Input and output tokens are billed at separate rates, and optional provider features may add extra charges.
What is the context length of Microsoft: Phi 4?
Microsoft: Phi 4 supports a context window of up to 16,384 tokens. Your provider may reserve part of that capacity for generated output or system instructions.
Which modalities does Microsoft: Phi 4 support?
Listed input modalities: text. Listed output modalities: text. Confirm feature availability with your chosen provider before integrating the model.
Where can I try Microsoft: Phi 4?
Use the Playground links above to check whether the model is currently available from those third-party services. Access, features, and pricing can vary between platforms.
AILesson · Recommended courses
Your next step: put AI to work
Go from understanding AI to getting things done. Practice prompting, reviewing, and improving results through interactive lessons for work and everyday life.

15 interactive lessons
AI for Beginners
Start a useful AI conversation, make the answer better, check what matters, and know when the next move is yours.
Explore this course
10 interactive lessons
ChatGPT Fundamentals
Learn ChatGPT through three practical workflows: complete a first chat, work from a file, then use Projects to carry a checked plan into a new chat.
Explore this course
7 interactive lessons
How Generative AI Works
Understand how common AI chats learn language patterns, use current messages, build replies, and add sources and tools.
Explore this course



