Skip to main content

Pricing

Runcrate offers three billable products: the Models API, GPU Instances, and Cloud Storage. All usage is deducted from your prepaid credit balance.

Models API

Models are billed per usage:
TypeBilling UnitNotes
Text models (Chat, Code, Reasoning)Per token (input + output)Varies by model
Image generationPer image generatedVaries by model and resolution
Video generationPer video generatedVaries by model and duration
Text-to-speechPer generationVaries by model and length
Speech-to-textPer audio minuteVaries by model
Pricing varies by model. Check the Model Catalog in the dashboard for current per-model rates.

GPU Instances

Instances are billed per hour while running. Approximate rates:
GPUVRAMApprox. Price/Hour
RTX 409024 GB~$0.30
L40S48 GB~$0.80
A100 40GB40 GB~$1.20
A100 80GB80 GB~$1.80
H10080 GB~$2.50
Prices are approximate and may vary based on availability. Check the deployment page for current pricing when you configure an instance.

Cloud Storage

ResourcePrice
Storage volume$0.03/GB/month (billed weekly)
No egress fees. You only pay for provisioned volume size.

Billing Rules

RuleDetails
Billing intervalHourly for instances, per-request for API, weekly for storage
Minimum spendNone — pay only for what you use
Minimum top-up$5
Terminate anytimeStop an instance at any time and stop being charged
Prepaid creditsAll usage is deducted from your credit balance
Egress feesNone

Cost Optimization Tips

Terminate Idle Instances

Instances are billed while running, even if idle. Terminate instances you are not actively using.

Use the Right GPU

Do not pay for an H100 when an RTX 4090 handles your workload. Start small and scale up only if needed.

Enable Auto-Recharge

Avoid losing work from unexpected termination. Set a threshold that gives you enough buffer time.

Monitor Burn Rate

Check your billing dashboard regularly to track spend and adjust usage patterns.