Shell

How it works

For running code, scripts, and command-line tools. Commands always run in a hosted environment, never on your machine.

1. 1

   Your model sends a batch of commands to run.

2. 2

   OpenRouter runs each one in an isolated Linux container and captures stdout, stderr, and the exit code.

3. 3

   Your model reads the output, and can run more commands in the same request.

Providers and pricing

Commands always run in the OpenRouter sandbox, on every model and provider. The Responses API’s native shell tool is accepted as a shorthand and runs in the same sandbox.

Standard model token costs apply to every request.

Using this tool

curl https://openrouter.ai/api/v1/responses \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai/gpt-5.2",
  "tools": [
    {
      "type": "openrouter:shell"
    }
  ],
  "input": "Create a Python script that prints the first 20 Fibonacci numbers and run it."
}'

Related tools

Code & execution

• Apply patch

  Let models propose file edits as V4A diffs

  Code & execution

• Bash

  Anthropic-style bash tool with optional sandboxed execution

  Code & execution