# Run an OpenAI Agents SDK agent in a sandbox

> The openai-agents-prized package is a sandbox client for the OpenAI Agents SDK: a SandboxAgent's commands and file edits run in a Prized sandbox, which is deleted when the run ends.

URL: https://prized.dev/docs/sandboxes-openai-agents

## 1. Install the package and export your keys [#1-install-the-package-and-export-your-keys]

```bash
pip install openai-agents-prized
export PRIZED_API_KEY=dcp_…
export OPENAI_API_KEY=…
```

It needs Python 3.10 or later and installs the OpenAI Agents SDK (`openai-agents`). Make the Prized key on [API keys](https://prized.dev/dashboard/workspace/api-keys) with **Full access**, or **Custom** with **Sandboxes: Write**.

## 2. Run an agent [#2-run-an-agent]

```python title="agent.py"
import asyncio

from agents import Runner
from agents.run import RunConfig
from agents.sandbox import SandboxAgent, SandboxRunConfig
from openai_agents_prized import PrizedSandboxClient, PrizedSandboxClientOptions

agent = SandboxAgent(name="coder", instructions="Work in the sandbox with your tools.")
sandbox = SandboxRunConfig(client=PrizedSandboxClient(), options=PrizedSandboxClientOptions(vcpu=2, memory_mb=4096))
task = "Write fizzbuzz.py, run it for 15, and show me the output."
result = asyncio.run(Runner.run(agent, task, run_config=RunConfig(sandbox=sandbox)))
print(result.final_output)
```

```bash
python agent.py
```

The agent's `exec_command`, `write_stdin` and `apply_patch` tools run in the sandbox as the user `prized` in `/home/prized/work`, and the sandbox is deleted when the run ends. It bills per second like any other ([Billing: Sandboxes](https://prized.dev/docs/billing#sandboxes)).

## Options [#options]

`PrizedSandboxClientOptions` takes the fields of a [create](https://prized.dev/docs/sandboxes-api#create): `template` (`prized-agent-v1` adds Claude Code and Codex), `vcpu`, `memory_mb`, `disk_gb`, `env_vars`, `labels`, `auto_pause_min`, `auto_delete_min` and `max_runtime_min`. Options written as a dict or JSON, for the SDK's `BaseSandboxClientOptions.parse`, name this client with `"type": "prized"`; the constructor sets it for you.

* **Pause instead of delete.** `pause_on_exit=True` pauses the sandbox at the end of a run, keeping memory and disk for the price of storage. A run resumed from its saved state continues in the same sandbox; without it, the resumed run gets a new sandbox with the workspace restored. If the pause fails, the sandbox is left running rather than deleted, and `client.delete(session)` raises so you can try again.
* **Moving from Runloop.** Replace `RunloopSandboxClient` and its options with `PrizedSandboxClient` and `PrizedSandboxClientOptions`; the agent stays the same. Runloop's `blueprint_name` becomes `template`, and `metadata` becomes `labels`.

## Limits [#limits]

* **No root.** No `sudo` or `apt` ([Inside a sandbox](https://prized.dev/docs/sandboxes#inside-a-sandbox)), so manifest users other than `prized`, manifest groups, and mounts are refused before a sandbox is created.
* **No ports.** Nothing reaches a sandbox from the internet.
* **Commands.** One that outlives `exec_command`'s wait keeps running until it exits, its `timeout` passes, or the run ends, and the agent checks on it or types into it with `write_stdin`. Output is kept up to 4 MiB a stream.
* **Failures.** A failed or cancelled create deletes its sandbox, and a failed resume pauses the sandbox again. A lost answer is checked against the sandbox's state, so a paused sandbox is never deleted by mistake. A sandbox paused during a run (`auto_pause_min`) is resumed by the next command; once the run has paused or deleted it, nothing the run sent late wakes it.
* **Lifetime.** 24 hours at most. On the [free tier](https://prized.dev/docs/sandboxes#free-tier): 60 minutes, 2 vCPU and 4 GB a sandbox, and 10 sandboxes at once.
* **Keys.** Code in the sandbox, the model's included, can read what you pass in `env_vars`. Keep your Prized key out of it.

A refusal from the API raises `PrizedAPIError`, whose `code` is the API's ([Errors](https://prized.dev/docs/sandboxes-api#errors)). Questions: the support address shown on https://prized.dev/docs/troubleshooting.