GPU Providers
A GPU provider is the cloud Socaity rents physical accelerators from to run your job. Socaity is the orchestrator that schedules the work, bills you for active time, and forwards container images to whichever provider you select. The provider is the layer that owns the GPU silicon, the data center, and the residency boundary; Socaity is the layer that owns the API contract and the job lifecycle.
The PROVIDER enum has six values: auto, localhost, socaity, runpod, scaleway, and azure. Working today: localhost and runpod. Reserved for future releases: scaleway and azure; both raise NotImplementedError at backend resolution. The socaity value routes a job through the Socaity orchestrator itself.
--provider flag values and backend resolution rules, see APIPod Providers. For region commitments, see EU Hosting & Data Sovereignty. No single cloud owns every GPU SKU, every region, and every certification profile you might need. RunPod has the broadest NVIDIA SKU coverage and the lowest per-second prices. Scaleway is an EU-headquartered cloud with ISO 27001 certified data centers in France. Azure offers H100 capacity and enterprise procurement. Socaity puts them behind one job API as interchangeable execution surfaces, so you can match a workload to the right surface without rewriting the integration.
The same image runs on any wired-up provider. Socaity hands the container to the provider, the provider runs it on a GPU, and Socaity returns the result through the same Job handle you already use. Switching providers is a flag change at deploy time, not a rewrite.
Serverless and dedicated NVIDIA GPUs across a broad SKU range. The current execution surface for every cloud Socaity job.
EU-headquartered cloud with ISO 27001 data centers in France. Reserved as a provider enum value; the backend resolver raises NotImplementedError today.
Microsoft Azure GPU VMs as a future execution surface. Reserved as a provider enum value; the backend resolver raises NotImplementedError today.
Status reflects the APIPod backend resolver today. Capability rows describe what each provider is positioned for; concrete numbers (per-second prices, GPU SKU availability, region coverage) live on each provider's own pricing page because they change faster than docs can. For Socaity-routed rates, see socaity.ai/Pricing.
| Dimension | RunPod | Scaleway | Azure |
|---|---|---|---|
| Status in APIPod | Working | Planned (NotImplementedError today) | Planned (NotImplementedError today) |
| Best fit | Serverless GPU jobs, scale-to-zero workloads, broad SKU coverage | EU-headquartered compute, GDPR-aligned procurement | Enterprise procurement and existing Azure commitments |
| Compute modes | Serverless and dedicated | Planned | Planned |
| GPU catalog | Picked in the RunPod dashboard at endpoint creation | Planned | Planned |
| Per-second pricing reference | socaity.ai/Pricing for Socaity-routed rates; RunPod console for direct rates | Planned | Planned |
| Region selection | Platform-selected (EU); --region flag accepted but not yet wired | Planned | Planned |
| Where it lives in the enum | PROVIDER.runpod | PROVIDER.scaleway | PROVIDER.azure |
Socaity does not maintain an in-product GPU SKU catalog. Each provider exposes its own hardware fleet, and you pick a SKU at the provider's surface (the RunPod dashboard, the Scaleway console, or the Azure portal) when you create the endpoint that consumes a Socaity-built image. The Socaity job model is hardware-agnostic: a model with sufficient VRAM runs the same way regardless of which NVIDIA generation backs it.
Hardware fit is bounded by model VRAM, not by API quotas. A 7B-parameter language model fits on a 16 GB card; a 70B model needs an A100 80 GB or H100. Pick the smallest GPU that holds your weights with headroom for the batch you intend to run. The socaity.ai/Pricing page lists currently-routed SKUs and per-second rates.
Region is a provider attribute, not a Socaity attribute. Today, region is selected by the platform (RunPod EU); the --region flag on apipod is accepted but not yet wired to provider routing, so per-workload selection is on the roadmap. APIPod itself does not enforce a region whitelist. Data residency follows the provider's own data-center footprint and certifications.
| Provider | Where regions are chosen | Data-residency footprint | Status |
|---|---|---|---|
runpod | RunPod EU, selected by the platform; --region flag not yet wired. | Per region (US, EU, APAC) | Working |
localhost | Wherever your host machine runs. Region is ignored. | Host-defined | Working |
scaleway | Planned. Scaleway operates EU data centers (France, Netherlands). | EEA (when wired) | Planned |
azure | Planned. Azure operates global regions including EU. | Per region (when wired) | Planned |
You want a serverless GPU endpoint today
Use
You are iterating locally before paying for GPU minutes
Use
You want APIPod to choose based on --compute
Use
You need ISO 27001 EU-headquartered hosting
Use
You need Azure procurement or enterprise commitments
Use
The provider is selected at deploy time. Three places set the value, in this precedence order: an explicit --provider flag on apipod, the APIPOD_PROVIDER env var, and the hard default localhost. Authentication keys are separate: SOCAITY_API_KEY authenticates the orchestrator for SDK and Socaity-routed calls; RUNPOD_API_KEY is read by the SDK when you bypass the Socaity backend with a direct RunPod service address.
# Working today
socaity build --provider runpod --compute serverless
socaity start --provider localhost
# Reserved enum values (raise NotImplementedError today)
# socaity build --provider scaleway
# socaity build --provider azure- APIPod Providers reference. The exact --provider flag values, backend resolution rules, and CLI examples.
- EU Hosting and data sovereignty. How region selection and provider choice map to GDPR posture.
- Build. How socaity scan and socaity build produce a provider-ready image.
- Deploy serverless. End-to-end flow for shipping an APIPod image to RunPod serverless today.