
1/ Any model on OpenRouter can now run code in a hosted Linux container. Add one tool to a Responses API request. The model writes the script, runs it, and reads back the result. Nothing to install, nothing to host. Meet openrouter:shell. To get started: "tools": [{ "type": "openrouter:shell", "parameters": { "engine": "openrouter" } }]
Adding one parameter now gives any model on OpenRouter a code-execution loop, removing the need to stand up and secure your own execution environment for tool-using agents.
Checking sign-in…
Loading comments…