Skip to content
Socaity Docs

Learning-oriented guides

Hands-on lessons that guide you through building something concrete with Socaity AI. Optimized for learning, not production use.

Platform Overview

Socaity AI is built around three layers that work in concert:

SDK (Python + JS)

Import AI models as functions. Works locally and in production. Available for Python and JavaScript.

APIPod

Build and deploy AI services. Wrap any model with a task endpoint and ship it to the cloud.

Cloud

Serverless or dedicated GPU hosting. Scales to zero between requests, with no DevOps overhead.

Tutorial 1 — Your First API Call

In this tutorial you'll install the Socaity SDK, import a model, and run your first inference.

01

Install the SDK

terminal
pip install socaity
02

Import a model

python
import os
from socaity import flux_schnell

flux = flux_schnell(api_key=os.getenv("SOCAITY_API_KEY"))
03

Run inference

python
result = flux(
    prompt="A cat wearing sunglasses on the moon",
    num_outputs=1,
).get_result()

result[0].save("my_first_image.png")

Tutorial 2 — Build & Deploy a Service

Build an image service with APIPod and deploy it to serverless GPU — no DevOps required.

01

Install APIPod

terminal
pip install apipod
02

Define a task endpoint

python
from apipod import APIPod

app = APIPod()

@app.endpoint("/generate")
def generate(prompt: str):
    return model.generate(prompt)
03

Deploy to the cloud

terminal
apipod --build

Unified socaity deploy CLI coming soon — it will mirror apipod for convenience.