sandbox.watch

OpenAI Hosted Sandboxes

https://developers.openai.com/api/docs/guides/agents-api/environments/openai-hosted

OpenAI Hosted Sandboxes provide a Linux workspace that an agent can use to run Python, Node.js, and command-line tools. OpenAI provisions and connects the sandbox, while the application supplies tasks and retrieves results.

Pricing model Eligible container sessions billed by the minute with a 5-minute minimum; memory-tier rates per 20-minute session per container; model usage billed separately.
Pricing The headline compute price as the provider states it. Sorting ranks prices stated per vCPU over time, converted to hourly. Other pricing models sort after, unranked. 1 GB: $0.03; 4 GB: $0.12; 16 GB: $0.48; 64 GB: $1.92 per 20-minute session per container
Free while idle Whether a stopped, paused, or sleeping sandbox costs nothing. –
Elastic Resources flex with what the sandbox actually uses, and the bill follows: yes when the provider bills on active or observed use, no when capacity is reserved or allocated and billed while it runs. ✕
Memory snapshots Whether RAM state survives a pause and resume, not just disk. –
Wake on request Whether a stopped sandbox wakes automatically on inbound traffic. –
Start / resume Typical time from create or resume to running. Sorting ranks stated times, converted to seconds; claims with no figure sort after, unranked. –
Max runtime The longest a sandbox may run. –
Isolation The isolation technology between sandboxes. –
GPUs Whether GPU instances are available for sandboxes. –
Docker Whether Docker containers can run inside the sandbox. –
SDKs Python, TypeScript

✓ yes · ✕ no · – no cited public fact.

A connected sandbox can be deleted after one hour without activity and keep-alives; the timeout is not configurable.

Sources

Last verified 2026-09-28. Corrections land through the update log.