Gemini 3.1 Flash Lite is Google's high-efficiency model optimized for high-volume, latency-sensitive use cases.
curl https://conduit-api.aurixel.ai/v1/chat/completions \
-H "Authorization: Bearer ck-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gemini-3.1-flash-lite","messages":[{"role":"user","content":"Hello!"}]}'→ OpenAI 兼容。加 "stream": true(配 "stream_options":{"include_usage":true})走流式。
推理强度:用模型名变体(-low / -agent);reasoning_effort 参数在 Gemini 上不可靠。