Sandbox guide

CompareSide by side

Two or three providers, head to head

Choose the providers you are deciding between. The table compares what they do across sixteen features; below it, the same providers are priced for a workload you can change. The link in the address bar keeps your choice.

16 providers16 featuresPlus a cost for your workload

Choose providers

Up to three. The first three are selected by default.

What each would cost

The same providers, priced for one workload. Open a row for the arithmetic.

Start from

The machine
How it runs
How busy it is

Only providers that bill for CPU actually used look at this. An agent waiting for messages is near 0%; a build or a test run is near 100%.

For providers that put an idle machine to sleep and wake it on a request: the share of its hours it has to be awake. An agent that only answers webhooks can sleep; one that holds a chat connection open cannot.

The AI model (optional)

For most agents the model costs more than the machine. Each message re-sends the agent's instructions and history, so tens of thousands of tokens is normal. Prices are the median of the providers that keep no data, from TokenWatch, read 2026-10-29.

    List prices only, excluding model tokens, egressData the machine sends out to the internet, such as downloads to a user or uploads to another service. Some providers charge per GB; most agents send very little., taxes and anything a provider does not publish. How the numbers are made.