Chat Completions
建立對話補全回應。支援文本生成、多模態輸入、函式呼叫、串流回應等功能。
端點
POST https://api.ofox.ai/v1/chat/completions請求參數
| 參數 | 類型 | 必填 | 說明 |
|---|---|---|---|
model | string | ✅ | 模型識別碼，如 openai/gpt-4o |
messages | array | ✅ | 訊息陣列 |
temperature | number | — | 取樣溫度 0-2，預設 1 |
max_tokens | number | — | 最大生成 token 數 |
stream | boolean | — | 是否啟用串流回應 |
top_p | number | — | 核取樣參數 |
frequency_penalty | number | — | 頻率懲罰 -2 到 2 |
presence_penalty | number | — | 存在懲罰 -2 到 2 |
tools | array | — | 可用工具定義（Function Calling） |
tool_choice | string/object | — | 工具選擇策略 |
response_format | object | — | 回應格式（JSON Mode） |
provider | object | — | OfoxAI 擴充：路由和回退設定 |
Message 格式
interface Message {
role: 'system' | 'user' | 'assistant' | 'tool'
content: string | ContentPart[] // 文字或多模態內容
name?: string
tool_calls?: ToolCall[] // assistant 訊息的工具呼叫
tool_call_id?: string // tool 訊息的呼叫 ID
}
// 多模態內容
type ContentPart =
| { type: 'text'; text: string }
| { type: 'image_url'; image_url: { url: string; detail?: 'auto' | 'low' | 'high' } }請求範例
cURL
Terminal
curl https://api.ofox.ai/v1/chat/completions \
-H "Authorization: Bearer $OFOX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4o",
"messages": [
{"role": "system", "content": "你是一個有幫助的助手。"},
{"role": "user", "content": "解釋什麼是 API Gateway"}
],
"temperature": 0.7
}'回應格式
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1703123456,
"model": "openai/gpt-4o",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "API Gateway（API 閘道）是一個..."
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 25,
"completion_tokens": 150,
"total_tokens": 175
}
}串流回應
設定 stream: true 啟用 SSE 串流回應：
Python
stream.py
stream = client.chat.completions.create(
model="openai/gpt-4o",
messages=[{"role": "user", "content": "講一個故事"}],
stream=True
)
for chunk in stream:
content = chunk.choices[0].delta.content
if content:
print(content, end="", flush=True)串流回應格式
每個 chunk 透過 SSE 發送：
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"你"},"finish_reason":null}]}
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"好"},"finish_reason":null}]}
data: {"id":"chatcmpl-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
data: [DONE]多模態輸入（視覺）
發送圖片讓模型分析：
response = client.chat.completions.create(
model="openai/gpt-4o",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "這張圖片裡有什麼？"},
{"type": "image_url", "image_url": {"url": "https://example.com/image.jpg"}}
]
}]
)支援視覺能力的模型包括：openai/gpt-4o、anthropic/claude-sonnet-4.5、google/gemini-3-flash-preview 等。
詳見 視覺理解指南。
Function Calling
詳見 函式呼叫指南。
Last updated on