Phi-4 — Especificaciones
Compiled by Mustafa Ihsan from the vendor’s published documentation · Last updated
| Desarrollador | Microsoft |
|---|---|
| Tipo | LLM (densa) |
| Modalidad | Texto → Texto |
| Parámetros | 14B |
| Ventana de contexto | 16K |
| Licencia | MIT (abierto) |
| Pesos abiertos | Sí |
| Lanzado | 2025 |
| Precio de entrada | $0.07 /1M |
| Precio de salida | $0.14 /1M |
| Proveedores de API | Azure, OpenRouter, Ollama |
Ejecútelo localmente
| VRAM (4 bits) | ~9 GB |
|---|---|
| GPU mínima | RTX 4070 12 GB / RTX 3060 12 GB |
What is Phi-4?
Phi-4 is Microsoft’s compact 14B reasoning model, MIT-licensed, which punches well above
its size on mathematics and logic. It needs about 9 GB of VRAM at 4-bit, running comfortably
on an RTX 4070 or RTX 3060 12GB, and costs $0.07 in / $0.14 out per million tokens
hosted.
The Phi line’s whole thesis is that curated, textbook-quality training data beats raw
scale for reasoning tasks, and Phi-4 is the clearest evidence for it — a 14B model competing
on maths and logic benchmarks with models several times larger. The cost of that focus is the
16K context window, by far the narrowest in this database and a hard limit for any workload
involving documents, long conversations or retrieval. Read it as a specialist: excellent for
structured reasoning over short inputs — maths tutoring, logic and code puzzles, deterministic
extraction from small payloads — and the wrong tool the moment your prompt grows. If you need
Phi-4’s reasoning with room to work, a 128K-context model in the same hardware bracket such
as Qwen3 14B is the better trade.
Phi-4 pricing: API cost per 1M tokens
| Entrada (por cada millón de tokens) | $0.0700 |
|---|---|
| Salida (por cada millón de tokens) | $0.140 |
| Relación salida/entrada | 2× |
| Combinada (4:1 entrada:salida) | $0.0840 por 1 millón de tokens |
What Phi-4 costs per month
Gasto mensual real con una mezcla entrada:salida de 4:1, es decir, la proporción que realmente genera una carga de trabajo típica de chat o RAG.
| Carga de trabajo | Tokens/mes | Coste mensual |
|---|---|---|
| Proyecto secundario | 1 millón de tokens de entrada / 0,25 millones de tokens de salida | $0.11 |
| Pequeño equipo | 20 millones de tokens de entrada / 5 millones de tokens de salida | $2.10 |
| Producción | 200 millones de tokens de entrada / 50 millones de tokens de salida | $21 |
Calcule sus propios números en la Calculadora de costos de API de IA.
Cheaper alternatives to Phi-4
| Modelo | Dólares por millón combinados | Usted ahorra |
|---|---|---|
| Mistral 7B abierta | $0.0220 | 74% cheaper |
| Llama 3.1 8B abierta | $0.0220 | 74% cheaper |
| Mistral NeMo 12B abierta | $0.0240 | un 71 % más barato |
¿Autoalojarlo o pagar por la API?
Phi-4 is open-weight, so you can run it yourself. It needs ~9 GB of VRAM at 4-bit (RTX 4070 12GB / RTX 3060 12GB). Self-hosting only beats the API once your volume is high enough to keep that hardware busy — the calculadora de autohospedaje frente a API calcula el punto de equilibrio para su volumen de tokens.
Preguntas frecuentes
How much does Phi-4 cost per 1M tokens?
Phi-4 costs $0.0700 per 1M input tokens and $0.140 per 1M output tokens. At a typical 4:1 input-to-output mix that blends to about $0.0840 per 1M tokens.
How much does Phi-4 cost per month?
A small-team workload of 20M input and 5M output tokens a month costs about $2.10 on Phi-4. A side project (1M in / 0.25M out) costs roughly $0.11.
What is a cheaper alternative to Phi-4?
Mistral 7B is the strongest cheaper option in our database at $0.0220 per 1M blended — about 74% less than Phi-4. It is also open-weight, so self-hosting is an option.
Can I run Phi-4 locally?
Yes. Phi-4 is open-weight and needs about ~9 GB of VRAM at 4-bit quantisation (RTX 4070 12GB / RTX 3060 12GB).
Why does Phi-4 charge more for output than input?
Output tokens are generated one at a time and cannot be batched the way a prompt can, so they cost the provider more to serve. Phi-4 charges 2× more for output, which is why prompt-heavy workloads are far cheaper to run than generation-heavy ones.
Los precios corresponden a las tarifas oficiales publicadas para la API principal del modelo y se revisan periódicamente conforme los proveedores los actualicen. No incluyen descuentos por volumen, procesamiento por lotes ni entradas en caché. Compare todos los modelos uno al lado del otro en la Base de datos de modelos de IA o el Clasificación de modelos de lenguaje grande (LLM).