第一次调用
非流式请求
curl http://YOUR_HOST:8000/v1/chat/completions \
-H "Authorization: Bearer wk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-flash",
"messages": [{"role": "user", "content": "你好"}]
}'响应:
{
"id": "chatcmpl-...",
"object": "chat.completion",
"model": "deepseek/deepseek-v4-flash",
"choices": [{ "message": { "role": "assistant", "content": "你好!" } }]
}流式请求(SSE)
加 "stream": true,响应以 data: {...} 逐块返回,以 data: [DONE] 结束。
curl -N http://YOUR_HOST:8000/v1/chat/completions \
-H "Authorization: Bearer wk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-flash",
"messages": [{"role": "user", "content": "介绍一下你自己"}],
"stream": true
}'YOUR_HOST 为你的网关域名或 IP(如 47.116.178.28:8000)。模型名格式为 provider/alias,可用模型列表见 模型列表。