Skip to main content

Documentation Index

Fetch the complete documentation index at: https://runinfra.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

L4, L40S, A100, H100, H200, B200.
The specific GPU region for a deployment is inferred from GPU availability at deploy time. Region pinning and data residency commitments are Enterprise-tier conversations. Contact sales if you need a region-locked deployment.
For compliance commitments including GDPR, DPAs, and signed data processing terms, contact sales.
RunInfra is SOC 2 Type 1 and Type 2 certified. Security posture and reports are available at the RightNow AI trust center (RunInfra is part of RightNow AI).
For HIPAA workloads and a signed BAA, contact sales.
No. Request and response data is not used for training any model. We log metadata (timestamps, token counts, status codes) for billing and debugging; the request and response bodies are retained only for the duration of your plan’s log retention window.
Yes. TLS 1.2+ everywhere. All traffic to the RunInfra API gateway is over HTTPS.
Per-API-key bearer tokens. Keys can be workspace-scoped or pipeline-scoped depending on how you create them in the dashboard. Keys can be rotated and revoked at any time from Settings > API Keys.
VPC peering and private-link deployments are Enterprise-tier conversations. Contact sales.

Not here?

GPUs and pricing

Tier-by-tier GPU availability and cost.

Regions

Region-specific availability.

Deployments

Flex vs Active, scaling.

Trust

SOC 2, HIPAA, DPA requests.