APIPod CLI Reference

APIPod CLI is the deployment tool — use it to scan a project, build a Docker container, and start your service. To interact with services from your code or terminal, see the SocaitySDK CLI.

Install with pip install apipod. APIPod ships a Python library (the @serverless decorator) and this CLI; the CLI is what you reach for at deploy time.

Installation

pip install apipod

Scan

Inspect your project and generate a deployment configuration. APIPod reads your requirements.txt, detects CUDA/PyTorch/TensorFlow dependencies, and infers the correct base Docker image.

# Scan the project and generate deployment config
apipod --scan

Build

Generate a Dockerfile and build your container. APIPod selects compatible CUDA/cuDNN versions automatically. Pass a target file to override the default entry point.

# Build with auto-detected settings
apipod --build

# Specify the target entry-point file
apipod --build ./main.py

Start

Run your service locally. Combine with --compute serverless --provider localhost to enable the in-memory job queue, which emulates serverless GPU behaviour for testing.

# Start on the default port (8000)
apipod --start

# Start on a custom port
apipod --start --port 9000

# Enable local job queue (emulates serverless GPU)
apipod --start --compute serverless --provider localhost

Deployment Flags

The deployment flags control which runtime backend APIPod selects. They work with both --build and --start.

# Build for Socaity orchestration
apipod --build --orchestrator socaity

# Build for RunPod serverless
apipod --build --compute serverless --provider runpod

# Start locally with serverless job-queue emulation
apipod --start --compute serverless --provider localhost

Flag Reference

Flag	Argument	Description
`--scan`	`(none)`	Scan project, detect dependencies, and generate deployment config.
`--build`	`[FILE]`	Build Docker container. Optionally specify the target entry-point file (defaults to main.py).
`--start`	`(none)`	Start the service locally.
`--orchestrator`	`socaity \| local`	Orchestration platform. Use "socaity" for Socaity-managed deployment.
`--compute`	`dedicated \| serverless`	Compute mode. "serverless" enables the job queue; "dedicated" runs a standard FastAPI server.
`--provider`	`localhost \| runpod \| auto`	Infrastructure provider. "localhost" activates in-memory job queue for local testing.
`--region`	`string`	Target deployment region (provider-dependent).
`--host`	`string`	Host address to bind to when starting locally (default: 0.0.0.0).
`--port`	`int`	Port to listen on when starting locally (default: 8000).

Orchestrator × Compute × Provider Matrix

The combination of --orchestrator, --compute, and --provider determines which runtime APIPod activates.

--orchestrator	--compute	--provider	Runtime
`socaity`	`serverless`	`localhost`	FastAPI + local job queue (test mode)
`socaity`	`serverless`	`runpod`	RunPod serverless router
`socaity`	`dedicated`	`localhost`	FastAPI + local job queue (test mode)
`socaity`	`dedicated`	`auto`	FastAPI
`local`	`serverless`	`localhost`	FastAPI + local job queue
`local`	`serverless`	`runpod`	RunPod serverless router
`local`	`dedicated`	`localhost`	FastAPI

Providers