# Use code interpreter

import { TypeScriptExample, Render } from "~/components";

<Render file="sdk-0x-note" product="sandbox" params={{ href: "/sandbox/", title: "Sandboxes" }} />

This guide shows you how to execute Python and JavaScript code with rich outputs using the Code Interpreter API.

## When to use code interpreter

Use the Code Interpreter API for **simple, direct code execution** with minimal setup:

- **Quick code execution** - Run Python/JS code without environment setup
- **Rich outputs** - Get charts, tables, images, HTML automatically
- **AI-generated code** - Execute LLM-generated code with structured results
- **Persistent state** - Variables preserved between executions in the same context

Use `exec()` for **advanced or custom workflows**:

- **System operations** - Install packages, manage files, run builds
- **Custom environments** - Configure specific versions, dependencies
- **Shell commands** - Git operations, system utilities, complex pipelines
- **Long-running processes** - Background services, servers

## Create an execution context

Code contexts maintain state between executions:

<TypeScriptExample>
```
import { getSandbox } from '@cloudflare/sandbox';

const sandbox = getSandbox(env.Sandbox, 'my-sandbox');

// Create a Python context
const pythonContext = await sandbox.createCodeContext({
  language: 'python'
});

console.log('Context ID:', pythonContext.id);
console.log('Language:', pythonContext.language);

// Create a JavaScript context
const jsContext = await sandbox.createCodeContext({
  language: 'javascript'
});
```
</TypeScriptExample>

## Execute code

### Simple execution

<TypeScriptExample>
```
// Create context
const context = await sandbox.createCodeContext({
  language: 'python'
});

// Execute code
const result = await sandbox.runCode(`
print("Hello from Code Interpreter!")
result = 2 + 2
print(f"2 + 2 = {result}")
`, { context: context.id });

console.log('Output:', result.output);
console.log('Success:', result.success);
```
</TypeScriptExample>

### State within a context

Variables and imports remain available between executions in the same context, as long as the container stays active:

<TypeScriptExample>
```
const context = await sandbox.createCodeContext({
  language: 'python'
});

// First execution - import and define variables
await sandbox.runCode(`
import pandas as pd
import numpy as np

data = [1, 2, 3, 4, 5]
print("Data initialized")
`, { context: context.id });

// Second execution - use previously defined variables
const result = await sandbox.runCode(`
mean = np.mean(data)
print(f"Mean: {mean}")
`, { context: context.id });

console.log(result.output); // "Mean: 3.0"
```
</TypeScriptExample>

:::note
Context state is lost if the container restarts due to inactivity. For critical data, store results outside the sandbox or design your code to reinitialize as needed.
:::

## Handle rich outputs

The code interpreter returns multiple output formats:

<TypeScriptExample>
```
const result = await sandbox.runCode(`
import matplotlib.pyplot as plt

plt.plot([1, 2, 3], [1, 4, 9])
plt.title('Simple Chart')
plt.show()
`, { context: context.id });

// Check available formats
console.log('Formats:', result.formats);  // ['text', 'png']

// Access outputs
if (result.outputs.png) {
  // Return as image
  return new Response(atob(result.outputs.png), {
    headers: { 'Content-Type': 'image/png' }
  });
}

if (result.outputs.html) {
  // Return as HTML (pandas DataFrames)
  return new Response(result.outputs.html, {
    headers: { 'Content-Type': 'text/html' }
  });
}

if (result.outputs.json) {
  // Return as JSON
  return Response.json(result.outputs.json);
}
```
</TypeScriptExample>

## Stream execution output

For long-running code, stream output in real-time:

<TypeScriptExample>
```
const context = await sandbox.createCodeContext({
  language: 'python'
});

const result = await sandbox.runCode(
  `
import time

for i in range(10):
    print(f"Processing item {i+1}/10...")
    time.sleep(0.5)

print("Done!")
`,
  {
    context: context.id,
    stream: true,
    onOutput: (data) => {
      console.log('Output:', data);
    },
    onResult: (result) => {
      console.log('Result:', result);
    },
    onError: (error) => {
      console.error('Error:', error);
    }
  }
);
```
</TypeScriptExample>

## Execute AI-generated code

Run LLM-generated code safely in a sandbox:

<TypeScriptExample>
```
// 1. Generate code with Claude
const response = await fetch('https://api.anthropic.com/v1/messages', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'x-api-key': env.ANTHROPIC_API_KEY,
    'anthropic-version': '2023-06-01'
  },
  body: JSON.stringify({
    model: 'claude-3-5-sonnet-20241022',
    max_tokens: 1024,
    messages: [{
      role: 'user',
      content: 'Write Python code to calculate fibonacci sequence up to 100'
    }]
  })
});

const { content } = await response.json();
const code = content[0].text;

// 2. Execute in sandbox
const context = await sandbox.createCodeContext({ language: 'python' });
const result = await sandbox.runCode(code, { context: context.id });

console.log('Generated code:', code);
console.log('Output:', result.output);
console.log('Success:', result.success);
```
</TypeScriptExample>

## Manage contexts

### List all contexts

<TypeScriptExample>
```
const contexts = await sandbox.listCodeContexts();

console.log(`${contexts.length} active contexts:`);

for (const ctx of contexts) {
  console.log(`  ${ctx.id} (${ctx.language})`);
}
```
</TypeScriptExample>

### Delete contexts

<TypeScriptExample>
```
// Delete specific context
await sandbox.deleteCodeContext(context.id);
console.log('Context deleted');

// Clean up all contexts
const contexts = await sandbox.listCodeContexts();
for (const ctx of contexts) {
  await sandbox.deleteCodeContext(ctx.id);
}
console.log('All contexts deleted');
```
</TypeScriptExample>

## Best practices

- **Clean up contexts** - Delete contexts when done to free resources
- **Handle errors** - Always check `result.success` and `result.error`
- **Stream long operations** - Use streaming for code that takes >2 seconds
- **Validate AI code** - Review generated code before execution

## Related resources

- [Code Interpreter API reference](/sandbox/sdk/api/interpreter/) - Complete API documentation
- [AI code executor tutorial](/sandbox/sdk/tutorials/ai-code-executor/) - Build complete AI executor
- [Execute commands guide](/sandbox/sdk/guides/execute-commands/) - Lower-level command execution