# Run Claude Code in a sandbox
URL: https://docs.munito.ai/sandboxes/cloud-agents/claude-code

## Sign in [#sign-in]

Use one of these three methods.

### With an Anthropic API key [#with-an-anthropic-api-key]

Put the key in the `env` of the sandbox:

```json
{ "ANTHROPIC_API_KEY": "sk-ant-..." }
```

Anthropic bills the usage to this key. See [authentication](https://code.claude.com/docs/en/authentication).

### With a Claude subscription [#with-a-claude-subscription]

1. Connect to the sandbox over [SSH](https://docs.munito.ai/sandboxes/ports-and-ssh#ssh).
2. Run `claude`.
3. Type `/login`, and select your Claude account.
4. Open the link on a device, and sign in with your Pro or Max plan.
5. Paste the code into the terminal.

- The sign-in stays in the sandbox. Each later `claude -p` command uses it.
- Claude Code uses the usage limits of your plan.
- A plan is for the work of one person. For many agents, use an API key.
- Anthropic does not let a third party collect or store the tokens of a Claude account ([legal and compliance](https://code.claude.com/docs/en/legal-and-compliance)). Do not put a token in an API request.

### With the open models of Munito AI [#with-the-open-models-of-munito-ai]

Put these variables in the `env` of the sandbox:

```json
{
  "ANTHROPIC_BASE_URL": "https://api.munito.ai/inference",
  "ANTHROPIC_AUTH_TOKEN": "munitoai_...",
  "ANTHROPIC_MODEL": "zai-org/glm-5.3-flash[1m]",
  "ANTHROPIC_DEFAULT_OPUS_MODEL": "zai-org/glm-5.3-flash[1m]",
  "ANTHROPIC_DEFAULT_SONNET_MODEL": "zai-org/glm-5.3-flash[1m]",
  "ANTHROPIC_DEFAULT_HAIKU_MODEL": "qwen/qwen3.8-27b"
}
```

- Use a Munito AI key with the **Inference** permission. The same key opens the sandboxes API.
- [Claude Code with open models](https://docs.munito.ai/agents/claude-code) explains each variable, the models and the regional hosts.

## Run a task [#run-a-task]

```bash
curl -sS --fail-with-body "https://api.munito.ai/sandboxes/v1/sandboxes/$SANDBOX/exec" \
  -H "Authorization: Bearer $MUNITO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"command": "cd /workspace && claude -p \"Write a Python script that prints the first 10 primes, and run it\" --allowedTools Bash Edit Write Read --output-format json", "timeout": 1800}'
```

- `claude -p` runs one task, and then it stops.
- `--allowedTools Bash Edit Write Read` lets Claude Code run commands and change files with no question.
- As root, Claude Code refuses `--dangerously-skip-permissions`. Use `--allowedTools`.
- `--output-format json` gives the result and the `session_id`.
- To get each event during the task, use `--output-format stream-json --verbose` and `"stream": true`.
- To continue a session, add `--resume <session_id>` to a later command.
- For a task of more than 30 minutes, start Claude Code in the background, and read its log with later commands:

```bash
nohup claude -p "..." --allowedTools Bash Edit Write Read > /workspace/claude.log 2>&1 &
```

## Use the terminal UI [#use-the-terminal-ui]

1. Add your public key with [SSH](https://docs.munito.ai/sandboxes/ports-and-ssh#ssh).
2. Connect with the command that `GET /sandboxes/{sandbox_id}/ssh` gives.
3. Run `claude`. The shell starts in `/workspace`, with the variables of the sandbox.

To keep the session after you disconnect, install `tmux` (`apt-get install -y tmux`), and start Claude Code in it.