v0
概觀
| 屬性 | 詳細資訊 |
|---|---|
| 說明 | v0 提供針對程式碼產生最佳化的 AI 模型，特別適合建立 Next.js 應用程式、React 元件與現代 Web 開發。 |
| LiteLLM 提供者路由 | v0/ |
| 提供者文件連結 | v0 API 文件 ↗ |
| Base URL | https://api.v0.dev/v1 |
| 支援的操作 | /chat/completions |
https://v0.dev/docs/v0-model-api
我們支援所有 v0 模型，只要在傳送 completion 請求時將 v0/ 設為前綴即可
可用模型
| 模型 | 說明 | 上下文視窗 | Max Output |
|---|---|---|---|
v0/v0-1.5-lg | 用於進階程式碼產生與推理的大型模型 | 512,000 tokens | 512,000 tokens |
v0/v0-1.5-md | 用於日常程式碼產生工作的中型模型 | 128,000 tokens | 128,000 tokens |
v0/v0-1.0-md | 舊版中型模型 | 128,000 tokens | 128,000 tokens |
必要變數
Environment Variables
os.environ["V0_API_KEY"] = "" # your v0 API key from v0.dev
注意：v0 API 存取需要 Premium 或 Team 方案。請前往 v0.dev/chat/settings/billing 升級。
用法 - LiteLLM Python SDK
非串流
v0 Non-streaming Completion
import os
import litellm
from litellm import completion
os.environ["V0_API_KEY"] = "" # your v0 API key
messages = [{"content": "Create a React button component with hover effects", "role": "user"}]
# v0 call
response = completion(
model="v0/v0-1.5-md",
messages=messages
)
print(response)
串流
v0 Streaming Completion
import os
import litellm
from litellm import completion
os.environ["V0_API_KEY"] = "" # your v0 API key
messages = [{"content": "Create a React button component with hover effects", "role": "user"}]
# v0 call with streaming
response = completion(
model="v0/v0-1.5-md",
messages=messages,
stream=True
)
for chunk in response:
print(chunk)
影像/多模態支援
所有 v0 模型都支援影像輸入，讓您可以將圖片與文字一併傳送：
v0 Vision/Multimodal
import os
import litellm
from litellm import completion
os.environ["V0_API_KEY"] = "" # your v0 API key
messages = [{
"role": "user",
"content": [
{
"type": "text",
"text": "Recreate this UI design in React"
},
{
"type": "image_url",
"image_url": {
"url": "https://example.com/ui-design.png"
}
}
]
}]
response = completion(
model="v0/v0-1.5-lg",
messages=messages
)
print(response)
函式呼叫
v0 支援用於結構化輸出的函式呼叫：
v0 Function Calling
import os
import litellm
from litellm import completion
os.environ["V0_API_KEY"] = "" # your v0 API key
tools = [
{
"type": "function",
"function": {
"name": "create_component",
"description": "Create a React component",
"parameters": {
"type": "object",
"properties": {
"component_name": {
"type": "string",
"description": "The name of the component"
},
"props": {
"type": "array",
"items": {"type": "string"},
"description": "List of component props"
}
},
"required": ["component_name"]
}
}
}
]
response = completion(
model="v0/v0-1.5-md",
messages=[{"role": "user", "content": "Create a Button component with onClick and disabled props"}],
tools=tools,
tool_choice="auto"
)
print(response)
用法 - LiteLLM Proxy
將下列內容加入您的 LiteLLM Proxy 設定檔：
config.yaml
model_list:
- model_name: v0-large
litellm_params:
model: v0/v0-1.5-lg
api_key: os.environ/V0_API_KEY
- model_name: v0-medium
litellm_params:
model: v0/v0-1.5-md
api_key: os.environ/V0_API_KEY
- model_name: v0-legacy
litellm_params:
model: v0/v0-1.0-md
api_key: os.environ/V0_API_KEY
啟動您的 LiteLLM Proxy 伺服器：
Start LiteLLM Proxy
litellm --config config.yaml
# RUNNING on http://0.0.0.0:4000
- OpenAI SDK
- LiteLLM SDK
- cURL
v0 via Proxy - Non-streaming
from openai import OpenAI
# Initialize client with your proxy URL
client = OpenAI(
base_url="http://localhost:4000", # Your proxy URL
api_key="your-proxy-api-key" # Your proxy API key
)
# Non-streaming response
response = client.chat.completions.create(
model="v0-medium",
messages=[{"role": "user", "content": "Create a React card component"}]
)
print(response.choices[0].message.content)
v0 via Proxy - Streaming
from openai import OpenAI
# Initialize client with your proxy URL
client = OpenAI(
base_url="http://localhost:4000", # Your proxy URL
api_key="your-proxy-api-key" # Your proxy API key
)
# Streaming response
response = client.chat.completions.create(
model="v0-medium",
messages=[{"role": "user", "content": "Create a React card component"}],
stream=True
)
for chunk in response:
if chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="")
v0 via Proxy - LiteLLM SDK
import litellm
# Configure LiteLLM to use your proxy
response = litellm.completion(
model="litellm_proxy/v0-medium",
messages=[{"role": "user", "content": "Create a React card component"}],
api_base="http://localhost:4000",
api_key="your-proxy-api-key"
)
print(response.choices[0].message.content)
v0 via Proxy - LiteLLM SDK Streaming
import litellm
# Configure LiteLLM to use your proxy with streaming
response = litellm.completion(
model="litellm_proxy/v0-medium",
messages=[{"role": "user", "content": "Create a React card component"}],
api_base="http://localhost:4000",
api_key="your-proxy-api-key",
stream=True
)
for chunk in response:
if hasattr(chunk.choices[0], 'delta') and chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="")
v0 via Proxy - cURL
curl http://localhost:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your-proxy-api-key" \
-d '{
"model": "v0-medium",
"messages": [{"role": "user", "content": "Create a React card component"}]
}'
v0 via Proxy - cURL Streaming
curl http://localhost:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer your-proxy-api-key" \
-d '{
"model": "v0-medium",
"messages": [{"role": "user", "content": "Create a React card component"}],
"stream": true
}'
如需有關使用 LiteLLM Proxy 的更詳細資訊，請參閱 LiteLLM Proxy 文件。
支援的 OpenAI 參數
v0 支援以下與 OpenAI 相容的參數：
| 參數 | 類型 | 說明 |
|---|---|---|
messages | array | 必要。具有 'role' 與 'content' 的訊息物件陣列 |
model | string | 必要。模型 ID (v0-1.5-lg, v0-1.5-md, v0-1.0-md) |
stream | boolean | 選用。啟用串流回應 |
tools | array | 選用。可用工具/函式清單 |
tool_choice | string/object | 選用。控制工具/函式呼叫 |
注意：與完整的 OpenAI API 相比，v0 支援的參數集合較少。像 temperature、max_tokens、top_p 等參數不受支援。
進階用法
自訂 API Base
如果您使用的是自訂的 v0 部署：
Custom API Base
import litellm
response = litellm.completion(
model="v0/v0-1.5-md",
messages=[{"role": "user", "content": "Hello"}],
api_base="https://your-custom-v0-endpoint.com/v1",
api_key="your-api-key"
)
定價
v0 模型需要 Premium 或 Team 訂閱。請前往 v0.dev/chat/settings/billing 取得目前定價資訊。