Python & JS Code Runner – Sandbox for AI Agents & Workflows
Pricing
from $0.80 / 1,000 code executions
Run Python or JavaScript (Node.js) code with JSON input in a fresh process: timeout with process-group kill, stdout/stderr capture, structured result, exit code, duration, pip/npm packages, batch jobs and dataset rows. Built for AI agents (MCP), n8n, Make and Zapier. Pay per execution.
You can access the Python & JS Code Runner – Sandbox for AI Agents & Workflows programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
1from apify_client import ApifyClient2
3# Initialize the ApifyClient with your Apify API token4# Replace '<YOUR_API_TOKEN>' with your token.5client = ApifyClient("<YOUR_API_TOKEN>")6
7# Prepare the Actor input8run_input = {9 "code": """# `input` holds the job's JSON input. Set `result` to return data (any JSON-serializable value).10import statistics11
12nums = input.get(\"numbers\", [])13print(f\"Got {len(nums)} numbers\")14result = {15 \"count\": len(nums),16 \"sum\": sum(nums),17 \"mean\": statistics.mean(nums) if nums else None,18 \"sorted\": sorted(nums),19}20""",21 "inputJson": { "numbers": [22 1,23 2,24 3,25 ] },26 "jobs": [27 {28 "id": "python-stats",29 "input": { "numbers": [30 4,31 8,32 15,33 16,34 23,35 42,36 ] },37 },38 {39 "id": "js-word-count",40 "language": "javascript",41 "code": """// `input` holds the job's JSON input. `return` a value (top-level await works).42const words = (input.text || '').toLowerCase().match(/[a-z']+/g) || [];43const counts = {};44for (const w of words) counts[w] = (counts[w] || 0) + 1;45console.log(`Counted ${words.length} words`);46return Object.entries(counts)47 .sort((a, b) => b[1] - a[1])48 .slice(0, 5)49 .map(([word, count]) => ({ word, count }));50""",51 "input": { "text": "The quick brown fox jumps over the lazy dog. The dog sleeps; the fox runs." },52 },53 ],54}55
56# Run the Actor and wait for it to finish57run = client.actor("gazidev/code-runner-sandbox").call(run_input=run_input)58
59# Fetch and print Actor results from the run's dataset (if there are any)60print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")61for item in client.dataset(run.default_dataset_id).iterate_items():62 print(item)63
64# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-startThe Apify API client for Python is the official library that allows you to use Python & JS Code Runner – Sandbox for AI Agents & Workflows API in Python, providing convenience functions and automatic retries on errors.
Install the apify-client
$pip install apify-clientOther API clients include: