How to beginner · 3 min read

How to use RunPod secure cloud

Q: How to use RunPod secure cloud

Use the runpod Python package to interact with RunPod's secure cloud by setting your API key in runpod.api_key. Create an Endpoint instance with your endpoint ID and call run_sync with your input to run inference securely in the cloud.

Quick answer

Use the runpod Python package to interact with RunPod's secure cloud by setting your API key in runpod.api_key. Create an Endpoint instance with your endpoint ID and call run_sync with your input to run inference securely in the cloud.

PREREQUISITES

Python 3.8+
RunPod API key
pip install runpod

Setup

Install the runpod Python package and set your API key from environment variables to authenticate with RunPod's secure cloud.

bash

pip install runpod

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 SDK to run inference on your secure cloud endpoint. Set your API key, create an Endpoint object with your endpoint ID, and call run_sync with your input prompt.

python

import os
import runpod

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

# Replace with your actual RunPod endpoint ID
endpoint_id = "YOUR_ENDPOINT_ID"

# Create an Endpoint instance
endpoint = runpod.Endpoint(endpoint_id)

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

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

# Print the output
print("Output:", result["output"])

output

Output: Hello, RunPod secure cloud! How can I assist you today?

Common variations

You can use asynchronous calls with run_async for non-blocking inference. Also, you can run serverless handlers inside RunPod pods by defining a handler function and starting the serverless environment.

python

import asyncio
import os
import runpod

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

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

asyncio.run(main())

output

Async 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, double-check your RunPod dashboard for the correct endpoint identifier.
For network timeouts, ensure your network allows outbound HTTPS requests to RunPod's API.

✅

Key Takeaways

Set runpod.api_key from environment variables for secure authentication.
Use Endpoint.run_sync for simple synchronous inference calls.
Use Endpoint.run_async for asynchronous, non-blocking calls.
Verify endpoint IDs and API keys in your RunPod dashboard to avoid errors.

Verified 2026-04

Verify ↗