OpenRouter 对比服务端代码执行工具：openrouter:shell 与 openrouter:bash
Insights — OpenRouter Blog
OpenRouter 推出 openrouter:shell 和 openrouter:bash 两款服务端代码执行工具，可在 API 请求期间于提供商沙箱内运行任意模型的命令，无需自行配置或加固容器。openrouter:shell 支持 Responses 和 Messages API，openrouter:bash 仅支持 Messages API；文章将这两款工具与 OpenAI、Anthropic、Google 为自家模型提供的代码执行能力在运行时、隔离、持久化和成本四方面进行对比。
正文
当前显示原文，中文全文译文尚未就绪。
A server-side code execution tool runs the model's commands in the provider's sandbox during your API request, so you don't provision or secure a container. OpenAI, Anthropic, and Google run code for their own models. Our openrouter:shell tool runs commands for any model on the Responses and Messages APIs, and our openrouter:bash tool does the same on the Messages API. This article compares the four on runtime, isolation, persistence, and cost, shows a complete request against our sandbox with the output it returned, and describes the jobs that still need a sandbox platform of your own.