Runtime vs SF Compute Autoresearch Sandboxes

Runtime costs $0.025 per vCPU-hour. SF Compute Autoresearch Sandboxes bills memory only, at $0.04572 per GiB-hour. Runtime runs Firecracker microVMs and has no session limit. SF Compute Autoresearch Sandboxes runs microVMs.

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

SF Compute Autoresearch Sandboxes

Isolated microVMs for AI agents that fork from a saved snapshot, part of SF Compute Autoresearch.

Isolation: MicroVM
Free tier: None
Max session: Not listed

Visit site SF Compute Autoresearch Sandboxes profile

What is different

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

Field

Runtime

SF Compute Autoresearch Sandboxes

vCPU, per hour: Runtime: $0.025; SF Compute Autoresearch Sandboxes: Included
RAM, per GiB-hour: Runtime: $0.0075; SF Compute Autoresearch Sandboxes: $0.04572
Storage: Runtime: $0.000119 per GiB-hour after 10 free GiB; SF Compute Autoresearch Sandboxes: Sandbox snapshots $0.10 per GiB-month of deduplicated bytes, $0.05 per GiB-month in cold storage
Free tier: Runtime: 100 hours of a 1 GB machine in the first 30 days; SF Compute Autoresearch Sandboxes: None
Billing: Runtime: Active CPU time only; SF Compute Autoresearch Sandboxes: Memory only
Largest sandbox: Runtime: 16 vCPU · 64 GiB; SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB
Concurrent sandboxes: Runtime: Up to 200; SF Compute Autoresearch Sandboxes: Up to 4,096
Isolation: Runtime: Firecracker microVM; SF Compute Autoresearch Sandboxes: MicroVM
Integrations: Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code; SF Compute Autoresearch Sandboxes: MCP, Claude Code

Full comparison

18 fields, at each provider's list price

Runtimewithruntime.com/pricingwithruntime.com

SF Compute Autoresearch Sandboxesautoresearch.sfcompute.com

Pricing

vCPU, per hour: Runtime: $0.025; SF Compute Autoresearch Sandboxes: Included
RAM, per GiB-hour: Runtime: $0.0075; SF Compute Autoresearch Sandboxes: $0.04572
Storage: Runtime: $0.000119 per GiB-hour after 10 free GiB; SF Compute Autoresearch Sandboxes: Sandbox snapshots $0.10 per GiB-month of deduplicated bytes, $0.05 per GiB-month in cold storage
Free tier: Runtime: 100 hours of a 1 GB machine in the first 30 days; SF Compute Autoresearch Sandboxes: None
Paid plan from: Runtime: Pay as you go; SF Compute Autoresearch Sandboxes: Pay as you go
Billing: Runtime: Active CPU time only; SF Compute Autoresearch Sandboxes: Memory only

Limits

Max session: Runtime: No limit; SF Compute Autoresearch Sandboxes: Not listed
Idle stop: Runtime: After 5 minutes; SF Compute Autoresearch Sandboxes: Not listed
Largest sandbox: Runtime: 16 vCPU · 64 GiB; SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB
Concurrent sandboxes: Runtime: Up to 200; SF Compute Autoresearch Sandboxes: Up to 4,096

Platform

Isolation: Runtime: Firecracker microVM; SF Compute Autoresearch Sandboxes: MicroVM
GPU: Runtime: No; SF Compute Autoresearch Sandboxes: Not listed
Snapshots: Runtime:; SF Compute Autoresearch Sandboxes:
Pause and resume: Runtime:; SF Compute Autoresearch Sandboxes:

Developer

SDKs: Runtime: JavaScript / TypeScript, Python, Go, Ruby, Java; SF Compute Autoresearch Sandboxes: Not listed
Integrations: Runtime: OpenAI Agents SDK, Vercel AI SDK, Claude Agent SDK, LangChain, MCP, Claude Code; SF Compute Autoresearch Sandboxes: MCP, Claude Code

Trust

License: Runtime: Not listed; SF Compute Autoresearch Sandboxes: Not listed
BYOC: Runtime: Not listed; SF Compute Autoresearch Sandboxes: Not listed

Hourly cost

One sandbox running for one hour

Size

Runtime

SF Compute Autoresearch Sandboxes

1 vCPU · 2 GiB: Runtime: $0.040; SF Compute Autoresearch Sandboxes: $0.091
2 vCPU · 4 GiB: Runtime: $0.080; SF Compute Autoresearch Sandboxes: $0.183
4 vCPU · 8 GiB: Runtime: $0.160; SF Compute Autoresearch Sandboxes: $0.366

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

Runtime fits when

You use the OpenAI Agents SDK, the Vercel AI SDK, the Claude Agent SDK or LangChain.
You want the lower list price: $0.080 against $0.183 an hour for 2 vCPU and 4 GiB.
You want to start without paying.
You need a desktop in the sandbox.

SF Compute Autoresearch Sandboxes fits when

You want one rate for memory, with CPU included.

More comparisons

See all comparisons

Runtime

SF Compute Autoresearch Sandboxes

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

Runtime fits when

SF Compute Autoresearch Sandboxes fits when

More comparisons

Related

Compare

Pricing

Browse