How to beginner · 3 min read

How to get started with RunPod

Q: How to get started with RunPod

Use the runpod Python package by setting your API key in runpod.api_key. Create an Endpoint instance with your RunPod endpoint ID, then call run_sync with your input prompt to get AI model output.

Quick answer

Use the runpod Python package by setting your API key in runpod.api_key. Create an Endpoint instance with your RunPod endpoint ID, then call run_sync with your input prompt to get AI model output.

PREREQUISITES

Python 3.8+
RunPod API key (set as environment variable RUNPOD_API_KEY)
pip install runpod

Setup

Install the runpod Python package and set your API key as an environment variable RUNPOD_API_KEY. This key authenticates your requests to RunPod's serverless AI endpoints.

bash

pip install runpod

# In your shell, set the API key:
# export RUNPOD_API_KEY=os.environ["RUNPOD_API_KEY"]

output

Collecting runpod
  Downloading runpod-1.0.0-py3-none-any.whl (10 kB)
Installing collected packages: runpod
Successfully installed runpod-1.0.0

Step by step

Use the runpod package to create an Endpoint object with your endpoint ID. Call run_sync with your input prompt to get the AI model's response.

python

import os
import runpod

# Set API key from environment
runpod.api_key = os.environ["RUNPOD_API_KEY"]

# Replace with your actual RunPod endpoint ID
endpoint_id = "YOUR_ENDPOINT_ID"
endpoint = runpod.Endpoint(endpoint_id)

# Input prompt for the model
input_data = {"prompt": "Hello, RunPod!"}

# Run inference synchronously
result = endpoint.run_sync({"input": input_data})

print("Model output:", result["output"])

output

Model output: Hello, RunPod! How can I assist you today?

Common variations

You can use run_async for asynchronous calls if your application supports async. Change the input structure depending on your model's requirements. RunPod supports various AI models, so adjust endpoint_id accordingly.

python

import asyncio
import os
import runpod

runpod.api_key = os.environ["RUNPOD_API_KEY"]
endpoint = runpod.Endpoint("YOUR_ENDPOINT_ID")

async def main():
    input_data = {"prompt": "Async call example"}
    result = await endpoint.run_async({"input": input_data})
    print("Async model output:", result["output"])

asyncio.run(main())

output

Async model output: Async call example received and processed.

Troubleshooting

If you get an authentication error, verify your RUNPOD_API_KEY environment variable is set correctly.
If the endpoint ID is invalid, check your RunPod dashboard for the correct endpoint identifier.
For network timeouts, ensure your internet connection is stable and retry.

✅

Key Takeaways

Set your RunPod API key in the environment variable RUNPOD_API_KEY before using the SDK.
Use runpod.Endpoint with your endpoint ID to interact with your deployed AI model.
Call run_sync or run_async to send inputs and receive outputs from RunPod.
Check your endpoint ID and API key carefully to avoid authentication or endpoint errors.

Verified 2026-04

Verify ↗