关于龙虾的配置分享

问题描述：

之前折腾龙虾也看了很多大佬的帖子，不过配置也折腾的很久才配置起来，现在分享一下完整的关于模型的配置

"models": { "mode": "merge", "providers": { "ggboom": { "baseUrl": "https://ai.qaq.al/v1", "apiKey": "xxx", "api": "openai-responses", "models": [ { "id": "gpt-5.2", "name": "GPT-5.2", "input": [ "text", "image" ], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 400000, "maxTokens": 128000 }, { "id": "gpt-5.4", "name": "GPT-5.4", "input": [ "text", "image" ], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 400000, "maxTokens": 128000 } ] }, "elysiver": { "baseUrl": "https://elysiver.h-e.top/v1", "apiKey": "xxx", "api": "openai-completions", "headers": { "User-Agent": "curl/8.0" }, "authHeader": true, "models": [ { "id": "gpt-5.2", "name": "gpt-5.2", "reasoning": true, "input": [ "text", "image" ], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 200000, "maxTokens": 16000 }, { "id": "gpt-5.2-xhigh", "name": "gpt-5.2-xhigh", "reasoning": true, "input": [ "text", "image" ], "cost": { "input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0 }, "contextWindow": 200000, "maxTokens": 16000 } ] } } }, "agents": { "defaults": { "model": { "primary": "ggboom/gpt-5.4", "fallbacks": [ "ggboom/gpt-5.2", "elysiver/gpt-5.2" ] }, "models": { "ggboom/gpt-5.2": { "alias": "gg-gpt-5.2" }, "ggboom/gpt-5.4": { "alias": "gpt-5.4" }, "elysiver/gpt-5.2": { "alias": "el-gpt-5.2" }, "elysiver/gpt-5.2-xhigh": { "alias": "gpt-5.2-xhigh" } }, "workspace": "/home/xxx/.openclaw/workspace", "compaction": { "mode": "safeguard" }, "maxConcurrent": 4, "subagents": { "maxConcurrent": 8 } } }

分别配置了ggboom和elysiver是可以正常运行，希望这个完整的配置可以帮助到需要的人

网友解答：

---

--【壹】--：

最好是上吧，看你需要用到它哪些功能

---

--【贰】--：

反代sk后，龙虾自己需要上境外的功能吗？

---

--【叁】--：

可以简单任务使用gemini或者deepseek，复杂任务再用gpt或者claude吗

---

--【肆】--：

我试一下，感谢博主的分析

---

--【伍】--：

感谢感谢

---

--【陆】--：

可以的，複製來，改改直接用