Skip to content
MODEL-AS-A-SERVICE
v2 · SDK Alpha · docs.socaity.ai

Any AI Service.
Deploy & Run.
One line.

Socaity runs AI services on European GPU infrastructure. Call a hosted service with one line of Python. Or wrap your own function with the APIPod decorator and deploy it to RunPod EU (Scaleway and Azure are planned). The same SDK covers both paths, and you pay only for GPU seconds spent in active processing.

your codeSocaity MaaSRunPod EU · Scaleway, Azure (planned)

One SDK. EU-resident compute. Active-only billing.

Two paths

Run AI

Consume models via SDK

Call any catalog model as a typed Python or JavaScript function. The SDK handles authentication, file uploads, job polling (1 s interval, 3600 s timeout), and result parsing.

Deploy AI

Publish your own services

Deploy any Python function as a service. The APIPod decorator generates the FastAPI surface and the Dockerfile; the CLI builds and pushes the image; the dashboard handles the deploy to serverless GPU on RunPod.

Model as a Service

Your Service. Your Model. Any Cloud.

We are on a mission to make AI models and services accessible to everyone, everywhere without the headache. Deploy privately or publish your API.

Your Code
Socaity MaaS
RunPod
Scaleway (planned)
Azure (planned)

Deploy Privately

Your models, your data, your infrastructure. Full control with private deployments.

Smart Routing

Choose your cloud provider and region. Deploy to RunPod, Scaleway, or Azure.

Active-Only Billing

Pay for inference time only. Zero cost for idle, boot, or failed attempts.

No Lock-In

Standard Docker packaging. Your code stays portable across any provider.

Run a service in five lines

python
import os
from socaity.sdk.replicate.black_forest_labs import flux_schnell

# flux_schnell() returns a client bound to the Socaity backend.
# get_result() blocks until the Job is terminal (default timeout 3600 s).
flux = flux_schnell(api_key=os.getenv("SOCAITY_API_KEY"))
result = flux(prompt="a cat on mars").get_result()
result.save("output.png")

Full Quick Start →

Reference and concepts

Tutorials

Worked examples from first model call to multi-model pipelines, each with runnable code.

Concepts

How the SDK, APIPod, and the routing layer that picks a provider for each call fit together, and where Jobs sit in that picture.

Platform

API keys, active-only billing, and the REST surface for calling Socaity without the SDK.

Latest changes: changelog →