Google Agent Platform Code Execution vs E2B

Google's managed code-execution sandbox for agents (formerly Vertex AI Agent Engine): sandboxes start and run code in under a second and keep their state for up to 14 days, with VPC Service Controls, CMEK and HIPAA support. For teams building agents on Google Cloud. A 2 vCPU / 4 GiB sandbox lists at $0.206 an hour on Google Agent Platform Code Execution against $0.166 on E2B, 24% more.

code-interpretergoogle-cloudhyperscalermanaged

Verified

Visit Google Agent Platform Code Execution Compare with E2B and others

Google Agent Platform Code Execution against E2B, line by line

E2B baseline sources
Field -E2B (baseline) +Google Agent Platform Code Execution Change
2 vCPU + 4 GiB, per hour $0.166 (source: E2B Pricing) $0.206 (source: Google Cloud Agent Platform pricing) +24%
vCPU, per hour $0.0504 (source: E2B Pricing) $0.085 (source: Google Cloud Agent Platform pricing) +69%
Memory, per GiB-hour $0.0162 (source: E2B Pricing) $0.009 (source: Google Cloud Agent Platform pricing) −44%
Billed on wall clock (source: E2B Pricing) not published Google Agent Platform Code Execution: no figure
Isolation Firecracker microVM (source: E2B homepage) gVisor (source: docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox) differs
Max session 1 h (Hobby), 24 h (Pro) (source: E2B Pricing) State kept up to 14 days (configurable TTL) (source: Code Execution overview) differs
Persistence state kept, pause/resume, memory kept, fork (source: E2B homepage) state kept (source: Code Execution overview) differs
Self-host Yes, Apache-2.0 (source: E2B runtime (GitHub)) not published Google Agent Platform Code Execution: no figure
Your own cloud (BYOC) Yes (source: E2B homepage) not published Google Agent Platform Code Execution: no figure
GPU No (source: E2B Pricing) not published Google Agent Platform Code Execution: no figure
SDKs Python, JavaScript/TypeScript (source: E2B Pricing) Runs Python (pre-installed libraries only) (source: Code Execution overview) differs
SOC 2 Type II (source: E2B homepage) not published Google Agent Platform Code Execution: no figure
Free tier Hobby: $0 plan fee, one-time $100 usage credit, 10 concurrent sandboxes, 1-hour sessions. (source: E2B Pricing) not published Google Agent Platform Code Execution: no figure

Prices are list prices for one hour of a 2 vCPU / 4 GiB sandbox: 2 × the vCPU rate + 4 × the memory rate. Each value links to the page it came from; not published means the vendor states no figure. How we compare.

Pick Google Agent Platform Code Execution instead of E2B when

  • your stack already runs on that cloud: Google Agent Platform Code Execution is a first-party service there, so identity, billing and networking stay in one place.

Stay on E2B when

  • you run model-written code you do not control and want a dedicated kernel per sandbox: E2B uses Firecracker microVMs, Google Agent Platform Code Execution uses gVisor.
  • pause has to keep running memory as well as files: E2B's pause saves both, and Google Agent Platform Code Execution does not state memory state in our data.
  • you need a SOC 2 report: E2B states Type II, and Google Agent Platform Code Execution states none in our data.
  • price decides it: Google Agent Platform Code Execution lists $0.206 an hour for the 2 vCPU / 4 GiB box against $0.166 on E2B.
  • you want managed cloud, your own cloud account and self-hosting from one vendor: E2B offers all three, with BYOC on its Enterprise plan.

All Google Agent Platform Code Execution facts

Source per value
Isolation Isolation technology the vendor states for each sandbox.
gVisor 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.
managed 1
Billing basis What the meter counts: wall-clock allocated resources, active CPU only, requests/plan quota, session-hours, or free software.
Not published
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.
$0.085 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.
$0.009 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).
Not published
Free tier A free plan, free monthly allowance or sign-up credit exists.
Not published
Free tier detail What the free tier or credit includes, as published.
Not published
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.
"Sandboxes can be created and execute code in under a second" 2
Max session length Longest single sandbox session by plan, as published.
State kept up to 14 days (configurable TTL) 2
Persistence / snapshots Filesystem state can be kept between runs (snapshots, persistent disks, volumes).
Yes 2
Pause / resume A sandbox can be paused, suspended, hibernated or put in standby and resumed later.
Not published
Memory state kept Pause/hibernate preserves running memory state, not only the filesystem.
Not published
Fork / branch A running or snapshotted sandbox can be cloned into new sandboxes.
No 2
GPU GPU sandboxes are offered.
Not published
Self-host Can run on your own hardware or cluster (open source or licensed).
Not published
BYOC / VPC Vendor-managed deployment inside your own cloud account.
Not published
Open source Core sandbox runtime is published under an open-source licence.
Not published
Licence Open-source licence of the runtime, if any.
Not published
SDKs / languages Official SDK languages (or supported execution languages where noted).
Runs Python (pre-installed libraries only) 2
Regions Published regions or region count.
Not published
Max vCPU per sandbox vCPU Largest published vCPU count per sandbox on any self-serve or enterprise plan.
Not published
Max memory per sandbox GiB Largest published memory per sandbox.
Not published
Concurrency Published concurrent sandbox limits by plan.
Not published
SOC 2 SOC 2 status as stated by the vendor.
Not published
HIPAA Vendor offers HIPAA-compliant usage/BAA (on any plan).
Yes 3
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.
$0.206 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.
1.24 1
Status Preview, experimental, beta, sunset or self-hosting caveats the vendor documents.
Not published
Pricing model
usage
From
$0.085 vCPU-hour
Pricing note
Billed as Agent Compute ($0.085/vCPU-h) and Agent Memory ($0.009/GiB-h) on allocated resources, rounded to the nearest second. Snapshots are not supported for Code Execution sandboxes; no network access. Pricing checked 2026-11-09.

Sources

  1. Google Cloud Agent Platform pricing accessed 2026-11-09
  2. Code Execution overview accessed 2026-11-09
  3. Agent Engine Code Execution (enterprise security) accessed 2026-11-09
  4. docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox accessed 2026-11-11

Google Agent Platform Code Execution in the E2B comparisons

Compare with other E2B alternatives

All 41

Get a quote from Google Agent Platform Code Execution and similar alternatives

Tell us what you need once. We send it to matching alternatives and they reply to you directly.

Quote requests open shortly. To get in first, email hello@e2balternatives.com.