curl https://api.deepseek.com/chat/completions \
-H “Content-Type: application/json” \
-H “Authorization: Bearer ${DEEPSEEK_API_KEY}” \
-d ‘{
“model”: “deepseek-v4-pro”,
“messages”: [
{“role”: “system”, “content”: “You are a helpful assistant.”},
{“role”: “user”, “content”: “Hello!”}
],
“thinking”: {“type”: “enabled”},
“reasoning_effort”: “high”,
“stream”: false
}’
V4两个模型的思考方式是根据 “thinking”: {“type”: “enabled”},这个参数确定的，而现在设置-模型-编辑模型内，没有设置思考强度的选项，希望官方增加一下。