SF Compute Autoresearch Sandboxes vs tama

SF Compute Autoresearch Sandboxes bills memory only, at $0.04572 per GiB-hour. tama costs $0.01166 per vCPU-hour. SF Compute Autoresearch Sandboxes runs microVMs. tama runs full VMs and offers GPUs.

Updated Oct 23, 2026

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

tama

Linux VMs with GPUs, billed by the second.

Isolation: Full VM
Free tier: Not listed
Max session: Not listed

Visit site tama profile

What is different

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

Field

SF Compute Autoresearch Sandboxes

tama

vCPU, per hour: SF Compute Autoresearch Sandboxes: Included; tama: $0.01166
RAM, per GiB-hour: SF Compute Autoresearch Sandboxes: $0.04572; tama: $0.005523
Storage: SF Compute Autoresearch Sandboxes: Sandbox snapshots $0.10 per GiB-month of deduplicated bytes, $0.05 per GiB-month in cold storage; tama: No charge for snapshots or stopped machines
Billing: SF Compute Autoresearch Sandboxes: Memory only; tama: Per second
Largest sandbox: SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB; tama: 32 vCPU · 128 GiB
Isolation: SF Compute Autoresearch Sandboxes: MicroVM; tama: Full VM

Full comparison

18 fields, at each provider's list price

SF Compute Autoresearch Sandboxesautoresearch.sfcompute.com

tamatama.computer

Pricing

vCPU, per hour: SF Compute Autoresearch Sandboxes: Included; tama: $0.01166
RAM, per GiB-hour: SF Compute Autoresearch Sandboxes: $0.04572; tama: $0.005523
Storage: SF Compute Autoresearch Sandboxes: Sandbox snapshots $0.10 per GiB-month of deduplicated bytes, $0.05 per GiB-month in cold storage; tama: No charge for snapshots or stopped machines
Free tier: SF Compute Autoresearch Sandboxes: None; tama: Not listed
Paid plan from: SF Compute Autoresearch Sandboxes: Pay as you go; tama: Pay as you go
Billing: SF Compute Autoresearch Sandboxes: Memory only; tama: Per second

Limits

Max session: SF Compute Autoresearch Sandboxes: Not listed; tama: Not listed
Idle stop: SF Compute Autoresearch Sandboxes: Not listed; tama: Not listed
Largest sandbox: SF Compute Autoresearch Sandboxes: 4 vCPU · 8 GiB; tama: 32 vCPU · 128 GiB
Concurrent sandboxes: SF Compute Autoresearch Sandboxes: Up to 4,096; tama: Not listed

Platform

Isolation: SF Compute Autoresearch Sandboxes: MicroVM; tama: Full VM
GPU: SF Compute Autoresearch Sandboxes: Not listed; tama:
Snapshots: SF Compute Autoresearch Sandboxes:; tama:
Pause and resume: SF Compute Autoresearch Sandboxes:; tama:

Developer

SDKs: SF Compute Autoresearch Sandboxes: Not listed; tama: Python, TypeScript
Integrations: SF Compute Autoresearch Sandboxes: MCP, Claude Code; tama: Not listed

Trust

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

Hourly cost

One sandbox running for one hour

Size

SF Compute Autoresearch Sandboxes

tama

1 vCPU · 2 GiB: SF Compute Autoresearch Sandboxes: $0.091; tama: $0.023
2 vCPU · 4 GiB: SF Compute Autoresearch Sandboxes: $0.183; tama: $0.045
4 vCPU · 8 GiB: SF Compute Autoresearch Sandboxes: $0.366; tama: $0.091

Compute only, at list rates.

Open the calculator

Which one fits

Based on the fields above

SF Compute Autoresearch Sandboxes fits when

You want each sandbox in its own microVM.
You use MCP or Claude Code.
You want one rate for memory, with CPU included.

tama fits when

You need GPUs.
You want each sandbox to be a full VM.
You want the lower list price: $0.045 against $0.183 an hour for 2 vCPU and 4 GiB.
You need a desktop in the sandbox.

More comparisons

See all comparisons

SF Compute Autoresearch Sandboxes

tama

What is different

Full comparison

Pricing

Limits

Platform

Developer

Trust

Hourly cost

Which one fits

SF Compute Autoresearch Sandboxes fits when

tama fits when

More comparisons

Related

Compare

Pricing

Browse