# E2B vs Prime Sandboxes: pricing, scale and snapshots Both give every sandbox a microVM and bill it while it runs. A 2 vCPU, 4 GiB job costs $2.76 on E2B and $1.52 on Prime Sandboxes. **Runtime costs 77% less than E2B and 58% less than Prime Sandboxes on the same job.** 1,000 one-minute runs of a 2 vCPU, 4 GiB sandbox with 20 CPU-seconds of work each are $2.76 on E2B, $1.52 on Prime and $0.64 on Runtime. Prime's rates are the lower of the two rivals'; Runtime's measured CPU undercuts both. ## At a glance | | E2B | Prime Sandboxes | Runtime | | -------------- | ------------------------------- | ---------------------------------------------- | -------------------------------------------------------- | | Isolation | Firecracker microVM, own kernel | Hardware-virtualized microVM, own guest kernel | Firecracker microVM, own kernel | | CPU | $0.0504 per allocated vCPU-hour | $0.02 per vCPU-hour while running | $0.025 per vCPU-hour of measured CPU, with a small floor | | Memory | $0.0162 per GiB-hour | $0.0125 per GiB-hour | $0.0075 per reserved GiB-hour | | Largest | 8 vCPUs and 8 GiB | 16 vCPUs, 64 GiB, 128 GiB of disk | 16 vCPUs and 64 GiB, paid | | At once | Set by plan | 1,024 per account to start | 100 paid; a new account 50 for a week | | Pause and fork | Pause keeps memory | Snapshots and forks listed as coming soon | Pause keeps memory; forks of a running sandbox | | Price terms | Hobby $0; Pro $150 a month | Published through 22 December 2026 | Fixed in each quote; no plan | ## Rates against features Prime is cheaper than E2B at every level of use here: its CPU rate is less than half of E2B's and its memory about a quarter lower. What E2B has that Prime does not yet is state: an E2B pause keeps memory and processes with no expiry, while Prime lists snapshots, and forking a sandbox mid-run, as coming soon. Prime starts accounts at 1,024 sandboxes at once, built for reinforcement learning rollouts. ## Cost for the same job 2 vCPU, 4 GiB, 60 seconds and 20 CPU-seconds a run, 1,000 runs, with Prime's default 5 GiB disk: ``` E2B CPU 1,000 × 60 s / 3,600 × 2 × $0.0504 = $1.68 Memory 1,000 × 60 s / 3,600 × 4 × $0.0162 = $1.08 Total $2.76 Prime CPU 1,000 × 60 s / 3,600 × 2 × $0.02 = $0.67 Memory 1,000 × 60 s / 3,600 × 4 × $0.0125 = $0.83 Disk 1,000 × 60 s / 3,600 × 5 × $0.0002 = $0.02 Total $1.52 Runtime CPU 1,000 × 20 s / 3,600 × $0.025 = $0.14 Memory 1,000 × 60 s / 3,600 × 4 × $0.0075 = $0.50 Total $0.64 ``` That is $276.00, $151.67 and $63.89 a month at 100,000 runs. With the CPUs busy for the whole minute, the job costs $2.76 on E2B, $1.52 on Prime and $1.33 on Runtime; Runtime stays cheapest because its memory is the cheapest. ## Which one to pick - **E2B** when paused sandboxes must stay forever, or you may self-host. - **Prime Sandboxes** for thousands of rollouts at once from the first day, inside Prime Intellect's training platform. - **Runtime** for agents and rollouts that wait on a model: the lowest bill, pause and forks today, and eval harnesses ([Harbor](/docs/harbor), [Inspect](/docs/inspect)) that switch without code changes. See [Runtime vs E2B](/docs/e2b-alternative) and [Runtime vs Prime Sandboxes](/docs/prime-sandboxes-alternative). ## Sources E2B rates checked 23 September 2026; Prime rates checked 25 September 2026. - [E2B pricing](https://e2b.dev/pricing), [E2B sandbox persistence](https://docs.e2b.dev/sandbox/persistence) - [Prime Sandboxes overview](https://docs.primeintellect.ai/sandboxes/overview), [Prime Sandboxes launch](https://www.primeintellect.ai/blog/sandboxes) - Runtime [pricing](/docs/pricing) Facts on this page were checked on 25 September 2026.