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 parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs. For more information, please see [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)
microsoft/phi-4
- Contexto
- 16k tokens
- Máx. completion
- 16,384
- Tools
- No
- JSON
- Sí
- Lanzamiento
- 2025-01-10
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "microsoft/phi-4",
"messages": [{"role": "user", "content": "Hola"}]
}'Preguntas frecuentes
- ¿Qué es 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 parameters, it was trained on a mix of high-quality synthetic datasets, data from curated websites, and academic materials. It has undergone careful improvement to follow instructions accurately and maintain strong safety standards. It works best with English language inputs. For more information, please see [Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905) Phi 4 corre en el API de Geek Hub (compatible con OpenAI). Id: microsoft/phi-4.
- ¿Phi 4 es gratis?
- No. El input cuesta $0.0763 / 1M tokens y el output $0.1526 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de Phi 4?
- Phi 4 tiene una ventana de 16k tokens. Soporta hasta 16,384 tokens de completion.
- ¿Phi 4 soporta tool calling y structured outputs?
- Phi 4 no publica tool calling en este endpoint. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó Phi 4?
- Phi 4 se lanzó el 10 de enero de 2025.