E2B: the baseline
Cloud sandboxes for AI agents: each sandbox is a Firecracker microVM that agents drive through Python and JS/TS SDKs. Built for teams shipping coding agents, data-analysis agents and computer-use agents. Its list price for a 2 vCPU / 4 GiB sandbox is $0.166 an hour. Every alternative page on this site sets its numbers against the ones below.
Verified
E2B facts
Source per value- Isolation Isolation technology the vendor states for each sandbox.
- Firecracker microVM 4
- Other isolation options Alternative runtimes the vendor offers besides the default (e.g. VM runtime, gVisor for GPU).
- Not published
- Deployment Managed cloud service, self-hosted software, or both.
- both 1
- Billing basis What the meter counts: wall-clock allocated resources, active CPU only, requests/plan quota, session-hours, or free software.
- wall clock 1
- vCPU price $/vCPU-hr Published on-demand CPU rate normalised to USD per vCPU-hour (per-second rates multiplied by 3,600; per-core rates divided by vCPUs per core where the vendor defines it). Lowest public tier, default region. 0 means the vendor states no separate CPU charge.
- $0.0504 1
- Memory price $/GiB-hr Published memory rate normalised to USD per GiB-hour (GB treated as GiB where the vendor does not distinguish). 0 means the vendor states memory is free.
- $0.0162 1
- Sandbox from $/sandbox-hr Smallest published per-sandbox hourly price, where the vendor publishes one.
- Not published
- Paid plan from $/mo Cheapest paid platform plan fee (before usage).
- $150.00 1
- Free tier A free plan, free monthly allowance or sign-up credit exists.
- Yes 1
- Free tier detail What the free tier or credit includes, as published.
- Hobby: $0 plan fee, one-time $100 usage credit, 10 concurrent sandboxes, 1-hour sessions. 1
- Cold start ms Vendor-published create/boot time in milliseconds (a vendor claim, not our benchmark). Only filled when the vendor publishes a number; see startup_claim for percentile and conditions.
- Not published
- Resume time ms Vendor-published resume-from-pause/standby/snapshot time in milliseconds.
- Not published
- Startup claim The vendor's startup/resume wording with conditions, quoted or closely paraphrased.
- Not published
- Max session length Longest single sandbox session by plan, as published.
- 1 h (Hobby), 24 h (Pro) 1
- Persistence / snapshots Filesystem state can be kept between runs (snapshots, persistent disks, volumes).
- Yes 4
- Pause / resume A sandbox can be paused, suspended, hibernated or put in standby and resumed later.
- Yes 4
- Memory state kept Pause/hibernate preserves running memory state, not only the filesystem.
- Yes 4
- Fork / branch A running or snapshotted sandbox can be cloned into new sandboxes.
- Yes 4
- GPU GPU sandboxes are offered.
- No 1
- Self-host Can run on your own hardware or cluster (open source or licensed).
- Yes 3
- BYOC / VPC Vendor-managed deployment inside your own cloud account.
- Yes 4
- Open source Core sandbox runtime is published under an open-source licence.
- Yes 3
- Licence Open-source licence of the runtime, if any.
- Apache-2.0 3
- SDKs / languages Official SDK languages (or supported execution languages where noted).
- Python, JavaScript/TypeScript 1
- Regions Published regions or region count.
- US, EU, APAC 4
- Max vCPU per sandbox vCPU Largest published vCPU count per sandbox on any self-serve or enterprise plan.
- 8 1
- Max memory per sandbox GiB Largest published memory per sandbox.
- 8 1
- Concurrency Published concurrent sandbox limits by plan.
- 10 (Hobby), 100 (Pro), 600/1,100 with add-ons 1
- SOC 2 SOC 2 status as stated by the vendor.
- Type II 4
- HIPAA Vendor offers HIPAA-compliant usage/BAA (on any plan).
- Not published
- 2 vCPU + 4 GiB per hour $/hr Hourly list price of one 2 vCPU / 4 GiB sandbox: 2 x the vCPU rate + 4 x the memory rate, from the two published rates. Left empty for self-hosted software and for vendors without both rates. Vendors that bill CPU only while busy (Vercel, Cloudflare, Upstash, Tensorlake, AWS AgentCore) cost less for idle agents than this shows.
- $0.1656 1
- Price vs E2B x E2B The 2 vCPU + 4 GiB hourly price divided by E2B's own ($0.1656 at $0.000014/vCPU-s and $0.0000045/GiB-s). Under 1 is cheaper than E2B.
- 1 1
- Status Preview, experimental, beta, sunset or self-hosting caveats the vendor documents.
- Not published
- Pricing note
- Published per second: $0.000014/vCPU-s, $0.0000045/GiB-s, disk free; hourly values are x3,600. Pro $150/mo + usage. Pricing checked 2026-11-09.
Sources
- E2B Pricing accessed 2026-11-11
- E2B Documentation accessed 2026-11-11
- E2B runtime (GitHub) accessed 2026-11-11
- E2B homepage accessed 2026-11-11
Why teams compare against E2B
- E2B alternatives cheaper than E2BWhich sandboxes cost less than E2B for the same box?
- Self-hosted E2B alternativesWhich E2B alternatives can I run on my own hardware or cluster?
- E2B alternatives with GPU sandboxesWhich E2B alternatives offer GPU sandboxes?
- E2B alternatives from AWS, Azure, Google Cloud, Alibaba and CloudflareWhich cloud providers sell a first-party E2B alternative?
- E2B alternatives with microVM or VM isolationWhich E2B alternatives give each sandbox its own kernel?
- All 41 E2B alternativesThe full sortable table, each row diffed against these numbers.