Modal vs Runtime

Modal costs $0.070956 per vCPU-hour and Runtime costs $0.025 per vCPU-hour. Modal runs gVisor, offers GPUs and limits a session to 24 hours. Runtime runs Firecracker microVMs and has no session limit.

Updated

Modal

Isolation
gVisor
Free tier
$30 credit every month
Max session
24 hours

Runtime

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

What is different

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

Modal
Runtime
vCPU, per hour
Modal: $0.070956
Runtime: $0.025
RAM, per GiB-hour
Modal: $0.024012
Runtime: $0.0075
Free tier
Modal: $30 credit every month
Runtime: 100 hours of a 1 GB machine in the first 30 days
Billing
Modal: Per second
Runtime: Active CPU time only
Max session
Modal: 24 hours
Runtime: No limit
Isolation
Modal: gVisor
Runtime: Firecracker microVM
GPU
Modal:
Runtime: No
SDKs
Modal: Python, JavaScript / TypeScript, Go
Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java
Integrations
Modal: Claude Agent SDK, Claude Code, LangChain
Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code

Full comparison

18 fields, at each provider's list price

Pricing

vCPU, per hour
Modal: $0.070956
Runtime: $0.025
RAM, per GiB-hour
Modal: $0.024012
Runtime: $0.0075
Storage
Modal: Not listed
Runtime: $0.000119 per GiB-hour after 10 free GiB
Free tier
Modal: $30 credit every month
Runtime: 100 hours of a 1 GB machine in the first 30 days
Paid plan from
Modal: Pay as you go
Runtime: Pay as you go
Billing
Modal: Per second
Runtime: Active CPU time only

Limits

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

Platform

Isolation
Modal: gVisor
Runtime: Firecracker microVM
GPU
Modal:
Runtime: No
Snapshots
Modal:
Runtime:
Pause and resume
Modal: Not listed
Runtime:

Developer

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

Trust

License
Modal: Not listed
Runtime: Not listed
BYOC
Modal: Not listed
Runtime: Not listed

Hourly cost

One sandbox running for one hour

Modal
Runtime
1 vCPU · 2 GiB
Modal: $0.119
Runtime: $0.040
2 vCPU · 4 GiB
Modal: $0.238
Runtime: $0.080
4 vCPU · 8 GiB
Modal: $0.476
Runtime: $0.160

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Modal fits when

  • You need GPUs.
  • You need SOC 2 Type II, HIPAA and GDPR.

Runtime fits when

  • A session must run longer than 24 hours.
  • You want each sandbox in its own microVM.
  • You use the OpenAI Agents SDK, the Vercel AI SDK or MCP.
  • You want the lower list price: $0.080 against $0.238 an hour for 2 vCPU and 4 GiB.

More comparisons

See all comparisons

Related