// scorecard · 60/100
verified 1mo agoAgent-readiness23/35
Agent registration (api_key)6/9
Public API5/5
OpenAPI spec0/9
MCP server9/9
llms.txt3/3
Reliability & performance0/15
Actively maintained—
Production-ready0/4
Updated recently—
Pricing12/13
Itemized public pricing6/6
Free tier / trial4/4
Free-tier generosity2/3
Docs & DX12/12
Docs quality8/8
Public API2/2
Quickstart / examples2/2
Security & compliance8/12
SOC 26/6
ISO 270010/2
GDPR0/2
Security / trust page2/2
Openness4/10
Open source0/6
Open / un-gated API4/4
Company maturity1/3
Company size1/2
Years operating—
// rankings · cost per standard workload
#7 in Code Sandboxes$82.8/ 1k sandbox-hrs
1 vCPU $0.000014/s + 2GiB x $0.0000045 = $0.000023/s x3.6M = $82.80/mo
e2b.dev/pricing// overview
E2B provides isolated sandboxes as secure Linux VMs that let agents safely execute code, process data, and run tools via SDKs in Python and JavaScript/TypeScript. It supports deep research agents, computer-use agents, automations, and related workloads with templates, volumes, commands, and lifecycle management. Case studies mention usage by Perplexity, Hugging Face, Groq, and others; the company raised a $21M Series A.
Best for: AI agents needing secure, customizable code-execution sandboxes
// pricing
Free tier · generosity 3/5
Includes: Hobby tier · $100 usage credits · Community support
Limits: 1-hour sandbox session · 20 concurrent sandboxes
HobbyFree + usage
- $100 one-time credits
- Community support
- 1-hour max session
- 20 concurrent sandboxes
Pro$150/mo + usage
- Everything in Hobby
- Custom CPU/RAM
- 24-hour max session
- 100 concurrent sandboxes
EnterpriseCustom
- Custom solution with special pricing
// security & compliance
✓ SOC 2✗ ISO 27001✗ GDPR✗ HIPAA
// features
- Isolated secure Linux sandboxes
- Custom CPU/RAM/storage per sandbox
- Session lengths up to 24 hours
- Concurrent sandbox limits (20-100+)
- Python & JS/TS SDKs with command streaming
- Templates, volumes, snapshots, and Git integration