microsoft/phi-4
16,384 context · $0.07/M input tokens · $0.14/M output tokens
Microsoft Research 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...
定价
按量付费
无需预付费用，仅按实际使用量付费
试用模型
API 使用
使用以下代码示例接入我们的 API：
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="microsoft/phi-4",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)模型介绍
Microsoft phi-4
microsoft phi-4
Why It Looks Great
- Large Language Model architecture for efficient processing
- 16384 context window for long document handling
- Competitive pricing at $0.1/$0.1 per million tokens
Key Features
- Context Window: 16384 tokens
- Max Output: 4096 tokens
- Vision: Supported
- Function Calling: Supported
Specifications
| Specification | Value |
|---|---|
| Provider | Microsoft |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 16384 tokens |
| Max Output | 4096 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
Pricing
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.1 |
| Output | $0.1 |
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- Submit — the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: microsoft/phi-4
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="microsoft/phi-4",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "microsoft/phi-4",
"messages": [{"role": "user", "content": "Hello!"}]
}'Notes
- Model: microsoft/phi-4
- Provider: Microsoft
信息
支持功能
API 访问指南
Phi 4 API
microsoft/phi-4
Microsoft Research 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...
输入
$0.065 /M
输出
$0.14 /M
上下文
16K
最大输出
16K
关于 Phi 4 的常见问题
Phi 4 API 多少钱?+
WaveSpeedAI 定价:输入每百万 token $0.07,输出每百万 token $0.14。Prompt 缓存和批处理单独计费,可显著降低长上下文、高重复任务的实际成本。
Phi 4 的上下文窗口是多大?+
Phi 4 单次请求最多支持 16K 上下文 token,输出最多 16K token。
Phi 4 是否兼容 OpenAI?+
是的。WaveSpeedAI 通过 https://llm.wavespeed.ai/v1 的 OpenAI 兼容端点提供 Phi 4。把官方 OpenAI SDK 的 base URL 指向该地址,使用 WaveSpeedAI 的 API Key 即可,无需任何其他代码改动。
如何开始使用 Phi 4?+
登录 WaveSpeedAI,在 Access Keys 中生成 API Key,使用上方显示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 发送请求。新账户可获得免费额度,用于试用 Phi 4。