Microsoft: Phi 4
- by microsoft
- microsoft/phi-4
[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...
What the numbers mean
- Context window16,384 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 12,000 words, or 25 pages.
- Max output14,745 tokens
- The longest single reply it can write: about 11,000 words.
- Input price$0.07 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$0.14 per million tokens
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs less than a cent.
- Modalitiestext in, text out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.
- Knowledge cutoff2024-06-30
- The last date its training data covers. It does not know about anything after that unless you put it in the prompt.
Supported parameters
The settings you can pass with a request. A model that lists tools can call functions; one that lists structured_outputs can be held to a JSON schema.
frequency_penaltylogit_biasmax_tokensmin_ppresence_penalty