Runtime vs Watasu

Runtime costs $0.025 per vCPU-hour. Runtime runs Firecracker microVMs and has no session limit. Watasu limits a session to 24 hours.

Updated Oct 23, 2026

Runtime

Firecracker microVM sandboxes for AI agents, billed on the CPU that code uses.

Isolation: Firecracker microVM
Free tier: 100 hours of a 1 GB machine in the first 30 days
Max session: No limit

Visit site Runtime profile

Watasu

Isolated Linux sandboxes for AI agents, hosted in the EU.

Isolation: Not listed
Free tier: Free Basic plan
Max session: 24 hours

Visit site Watasu profile

What is different

8 fields differ. The rest are the same or not listed.

Field

Runtime

Watasu

Storage: Runtime: $0.000119 per GiB-hour after 10 free GiB; Watasu: Retained disks €0.10 per GiB per month while the sandbox is stopped. Checkpoints and templates €0.03 per GiB per month.
Free tier: Runtime: 100 hours of a 1 GB machine in the first 30 days; Watasu: Free Basic plan
Billing: Runtime: Active CPU time only; Watasu: Per second
Max session: Runtime: No limit; Watasu: 24 hours
Largest sandbox: Runtime: 16 vCPU · 64 GiB; Watasu: 8 vCPU · 8 GiB
Concurrent sandboxes: Runtime: Up to 200; Watasu: Up to 100
SDKs: Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java; Watasu: Python, TypeScript, Rust
Integrations: Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code; Watasu: MCP, Claude Code

Full comparison

18 fields, at each provider's list price

Runtimewithruntime.com/pricingwithruntime.com

Watasuwatasu.io/pricing

Pricing

vCPU, per hour: Runtime: $0.025; Watasu: Not listed
RAM, per GiB-hour: Runtime: $0.0075; Watasu: Not listed
Storage: Runtime: $0.000119 per GiB-hour after 10 free GiB; Watasu: Retained disks €0.10 per GiB per month while the sandbox is stopped. Checkpoints and templates €0.03 per GiB per month.
Free tier: Runtime: 100 hours of a 1 GB machine in the first 30 days; Watasu: Free Basic plan
Paid plan from: Runtime: Pay as you go; Watasu: Not listed
Billing: Runtime: Active CPU time only; Watasu: Per second

Limits

Max session: Runtime: No limit; Watasu: 24 hours
Idle stop: Runtime: After 5 minutes; Watasu: Not listed
Largest sandbox: Runtime: 16 vCPU · 64 GiB; Watasu: 8 vCPU · 8 GiB
Concurrent sandboxes: Runtime: Up to 200; Watasu: Up to 100

Platform

Isolation: Runtime: Firecracker microVM; Watasu: Not listed
GPU: Runtime: No; Watasu: Not listed
Snapshots: Runtime:; Watasu:
Pause and resume: Runtime:; Watasu:

Developer

SDKs: Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java; Watasu: Python, TypeScript, Rust
Integrations: Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code; Watasu: MCP, Claude Code

Trust

License: Runtime: Not listed; Watasu: Not listed
BYOC: Runtime: Not listed; Watasu: Not listed

Hourly cost

One sandbox running for one hour

Size

Runtime

Watasu

1 vCPU · 2 GiB: Runtime: $0.040; Watasu: Not listed
2 vCPU · 4 GiB: Runtime: $0.080; Watasu: Not listed
4 vCPU · 8 GiB: Runtime: $0.160; Watasu: Not listed

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Runtime fits when

A session must run longer than 24 hours.
You use the OpenAI Agents SDK, the Vercel AI SDK, the Claude Agent SDK or LangChain.
You need a desktop in the sandbox.
Your code waits a lot: CPU is billed only while it is in use.

More comparisons

See all comparisons

Runtime

Watasu

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Runtime fits when

More comparisons

Related

Compare

Pricing

Browse