# Prime Sandboxes alternatives: agent sandboxes ranked by cost Runtime is the cheapest Prime Sandboxes alternative for rollouts that wait on a model: 58% less per job, with forks today. **Runtime runs the same job for 58% less than Prime Sandboxes.** 1,000 one-minute runs of a 2 vCPU, 4 GiB sandbox, each busy for 20 CPU-seconds, cost $0.64 on Runtime and $1.52 on Prime, or $63.89 against $151.67 at 100,000 runs a month. Prime's CPU rate is the lowest of any allocated provider here, but it bills every vCPU for the whole run. Prime rates checked 25 September 2026; the others checked 23 September 2026. ## Why compare Prime Sandboxes with others? Prime Intellect built its sandboxes for agentic reinforcement learning: hardware-virtualized microVMs, room for 1,024 per account, and rates it calls the most competitive on the market. Three things still send teams to compare: - **Rollouts mostly wait.** A policy model thinks while the environment idles. Prime bills the vCPUs, memory and disk a sandbox was given while it runs, so the idle time is charged in full. - **State between steps.** Saving, restoring and forking a sandbox mid-run are listed as coming soon. Branching an environment into several rollouts, or keeping one warm between training steps, needs them today. - **Launch pricing.** The published rates hold through 22 December 2026. A budget planned past that date has no published figure to plan on. ## Which alternatives are cheapest? Sixteen rows, one job: 1,000 runs of 60 seconds on a 2 vCPU, 4 GiB sandbox with 20 CPU-seconds of work each. Prime lands fifth. [Pricing](/docs/pricing#published-rate-comparison) shows each row's arithmetic without plan fees, idle storage, network or credits. | # | Provider | Isolation | CPU billed on | 1,000 runs | | --- | -------------------------------------------------------- | ------------------------------------------ | --------------------------------------- | ---------: | | 1 | **Runtime** | Firecracker microVM, own kernel | Measured CPU, with a small floor | **$0.64** | | 2 | Northflank | microVMs for CPU work, gVisor for GPU work | Allocated vCPUs | $1.11 | | 3 | Cloudflare Sandbox (2 vCPU, 6 GiB, 12 GB disk) | A container in its own VM | Active CPU | $1.35 | | 4 | Fly Machines, `performance-2x` with 4 GB | Firecracker microVM | The machine's size while started | $1.44 | | 5 | Prime Sandboxes (5 GiB disk) (the one you are replacing) | microVM, own guest kernel | Allocated vCPUs while running | $1.52 | | 6 | Morph, 2 MCUs | Full virtual machines | The machine's size in MCUs | $1.67 | | 7 | Vercel Sandbox, `iad1` (4 GB) | Firecracker microVM, own kernel | Active CPU | $2.12 | | 8 | Freestyle (32 GiB disk) | Full Linux virtual machines | Allocated vCPUs | $2.25 | | 9 | CodeSandbox SDK, a Nano VM | Firecracker microVM | The VM's size, by the minute rounded up | $2.48 | | 10 | E2B | Firecracker microVM, own kernel | Allocated vCPUs | $2.76 | | 11 | Daytona | Containers by default; VM class separate | Allocated vCPUs | $2.76 | | 12 | Blaxel (4 GB) | Lightweight virtual machines | Included with memory, active time | $2.76 | | 13 | Fly Sprites (4 GB in use) | Firecracker microVM | Measured CPU | $3.31 | | 14 | Modal Sandboxes (1 physical core) | gVisor, a user-space kernel | Requested or used, whichever is higher | $3.97 | | 15 | AWS Lambda MicroVMs, Arm | Firecracker microVM | Baseline vCPUs while running | $4.20 | | 16 | Runloop, a `MEDIUM` devbox | microVM, with a container inside | Allocated CPUs while running | $5.33 | ## Cost for the same job Runtime, Prime, Northflank (the only allocated provider cheaper than Prime) and Modal (a common choice for RL research) in full: ``` 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 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 Northflank CPU 1,000 × 60 s / 3,600 × 2 × $0.01667 = $0.556 Memory 1,000 × 60 s / 3,600 × 4 × $0.00833 = $0.555 Total $1.11 Modal CPU 1,000 × 60 s × 1 core × $0.00003942 = $2.37 Memory 1,000 × 60 s × 4 × $0.00000667 = $1.60 Total $3.97 ``` If the rollout kept both CPUs busy for the whole minute, the job would cost $1.33 on Runtime, $1.52 on Prime, $1.11 on Northflank and $3.97 on Modal. Prime charges the same either way; Runtime's figure rises with the work and still comes in under Prime's, because Runtime's memory is $0.005 a GiB-hour cheaper. ## The alternatives, for a Prime Sandboxes user ### 1. Runtime: measured CPU and forks today Each sandbox is a Firecracker microVM with its own kernel. CPU is $0.025 per vCPU-hour of measured use, never below a twentieth of a vCPU, and memory $0.0075 per reserved GiB-hour. A paid sandbox takes up to 16 vCPUs and 64 GiB, the same ceiling as Prime. Pause keeps memory and processes for 1 to 365 days, and a fork turns one running environment into up to 10 copies. The Harbor and Inspect integrations run eval suites, Terminal-Bench among them. ### 2. Northflank: the lowest allocated rates $0.01667 per vCPU-hour and $0.00833 per GB-hour, $1.11 for this job, and GPUs by the hour. Each sandbox is a service with a deployment plan. ### 3. Modal Sandboxes: GPUs beside the training code gVisor rather than a microVM, CPU on the larger of request and use, $3.97 here. Modal's pull is running sandboxes next to GPU functions in one platform. ### 4. Morph: branching at scale $0.05 per MCU-hour, and Infinibranch forks a running machine, memory included, into hundreds of replicas. ### 5. Daytona: GPUs and a large free start E2B's rates, $2.76 here, with GPU sandboxes and $200 of free compute. ## Moving rollouts to Runtime Set the environment up once, then fork it for each rollout so none of them repeats the install: ```python check from withruntime import Sandbox with Sandbox.create(funding="paid") as env: env.exec("pip install --quiet gymnasium") rollouts = env.fork(count=8) # eight running copies, memory included for rollout in rollouts: print(rollout.exec("python3 -c 'import gymnasium; print(gymnasium.__version__)'").stdout) rollout.stop() ``` Harbor and Inspect users can switch the environment instead of the code: [Harbor](/docs/harbor) and [Inspect](/docs/inspect). For the full picture read [Runtime vs Prime Sandboxes](/docs/prime-sandboxes-alternative), or price a rollout in the [Prime Sandboxes pricing calculator](/calculators/prime-sandboxes-pricing-calculator). ## Sources Prime Sandboxes checked 25 September 2026; Northflank, Modal, Morph and Daytona rates checked 23 September 2026. - [Prime Sandboxes overview](https://docs.primeintellect.ai/sandboxes/overview), [Prime Sandboxes launch](https://www.primeintellect.ai/blog/sandboxes) - [Northflank pricing](https://northflank.com/pricing) - [Modal pricing](https://modal.com/pricing) - [Morph Cloud pricing](https://cloud.morph.so/web/pricing), [Daytona pricing](https://www.daytona.io/pricing) - Runtime [pricing](/docs/pricing)