Grok 4.5 API
由 xAI 提供支援的 Grok 4.5 LLM 模型完整 API 參考文件。
模型變體
此 API 支援兩種 Grok 4.5 模型變體:
快速比較
Grok 4.5 文字轉文字
端點
POST /api/v1/chat/completions
請求參數
必要
訊息支援
選用
請求範例
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Accept': 'text/event-stream',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'grok-4.5-text-to-text',
messages: [
{
role: 'user',
content: 'Explain the key differences between REST and GraphQL APIs.'
}
],
stream: true,
max_tokens: 2048
})
});
Grok 4.5 圖片轉文字
端點
POST /api/v1/chat/completions
請求參數
必要
訊息支援
選用
請求範例
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
method: 'POST',
headers: {
'Authorization': 'Bearer YOUR_API_KEY',
'Accept': 'text/event-stream',
'Content-Type': 'application/json'
},
body: JSON.stringify({
model: 'grok-4.5-image-to-text',
messages: [
{
role: 'user',
content: [
{ type: 'text', text: 'Describe the image and extract any visible text.' },
{
type: 'image_url',
image_url: {
url: 'https://example.com/sample-image.jpg'
}
}
]
}
],
stream: true,
max_tokens: 2048
})
});
回應格式
Grok 4.5 LLM 模型會傳回與 OpenAI 相容的補全回應。使用 stream: true 時,回應為伺服器傳送事件;使用 stream: false 時,回應為單一 JSON 物件。
成功回應
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"grok-4.5-text-to-text","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"grok-4.5-text-to-text","choices":[{"index":0,"delta":{"content":"Here is a concise explanation"},"finish_reason":null}]}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"grok-4.5-text-to-text","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"grok-4.5-text-to-text","choices":[],"usage":{"prompt_tokens":12,"completion_tokens":8,"total_tokens":20}}
data: [DONE]
錯誤回應
event: error
data: {"error":{"message":"API requests too frequent, exceeding rate limit","type":"rate_limit_error","code":"1302","param":null}}
最佳實務
- 使用結構化訊息: 透過
messages[] 傳送對話記錄,而不是將上下文合併為一個提示詞。
- 選擇正確的模型變體: 純文字推理使用文字轉文字,需要理解圖片時使用圖片轉文字。
- 接收 SSE 事件: 將
choices[0].delta.content 附加至串流顯示內容,並將 data: [DONE] 視為成功完成。
- 僅傳送支援的輸入: 文字轉文字不支援圖片或檔案附件。