// scorecard · 46/100
verified 1mo agoAgent-readiness20/35
Agent registration (api_key)6/9
Public API5/5
OpenAPI spec0/9
MCP server9/9
llms.txt0/3
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 & DX4/12
Docs quality—
Public API2/2
Quickstart / examples2/2
Security & compliance6/12
SOC 26/6
ISO 270010/2
GDPR0/2
Security / trust page0/2
Openness4/10
Open source0/6
Open / un-gated API4/4
Company maturity0/3
Company size—
Years operating—
// rankings · cost per standard workload
#16 in Code Sandboxesnot comparable
Per-request, not per-hour (Pro $250/mo=1M req); no compute-time rate. Not derivable
riza.io/pricing// overview
Riza gives LLMs the ability to run code via a secure, isolated execution environment with REST APIs and SDKs for Python, TypeScript, and Go. It supports Python, JS/TS, Ruby, and PHP, with features including <10ms startup, configurable env vars/network/files, custom runtimes, and self-hosting. It is used for LLM-generated code, data analysis/visualization, agent tools, data extraction, user code execution, and evals.
Best for: AI apps and agents that need to safely execute LLM-written code at scale
// pricing
Free tier · generosity 4/5
Includes: Hobby plan access
Limits: 100,000 requests/month · 30s execution time · 3 custom runtimes
HobbyFree
- Up to 100,000 requests/month
- 30-second execution limit
- 3 Custom Runtimes
- Community Discord support
Pro$250/month
- 1,000,000 requests/month
- Up to 15-minute execution limit
- 50 Custom Runtimes
- Dedicated Slack support
EnterpriseCustom
- Custom request quota
- Self-hosting available
// security & compliance
✓ SOC 2✗ ISO 27001✗ GDPR✗ HIPAA
// features
- Secure isolated execution (WebAssembly)
- No cold starts (<10ms)
- API-first with Python/TS/Go SDKs
- Configurable env vars, network, files, stdin
- Custom runtimes and third-party packages
- Self-hosting on Kubernetes