> ## Documentation Index
> Fetch the complete documentation index at: https://docs.hitheo.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Generate Code

> Generate production-quality code using the Theo Code engine.

Generate code from a natural language prompt. The Theo Code engine is optimized for production-quality code and long-form output.

## Authentication

Requires a Bearer token. See [Authentication](/api-reference/authentication).

## Request Body

<ParamField body="prompt" type="string" required>
  Description of the code to generate.
</ParamField>

<ParamField body="language" type="string">
  Target programming language (e.g., `"typescript"`, `"python"`, `"go"`, `"rust"`). Appended as a hint to the engine.
</ParamField>

<ParamField body="framework" type="string">
  Target framework (e.g., `"express"`, `"nextjs"`, `"fastapi"`, `"gin"`). Appended as a hint to the engine.
</ParamField>

## Request Examples

<CodeGroup>
  ```bash curl theme={null}
  curl -X POST https://www.hitheo.ai/api/v1/code \
    -H "Authorization: Bearer $THEO_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "prompt": "Write a TypeScript Express middleware for JWT authentication",
      "language": "typescript",
      "framework": "express"
    }'
  ```

  ```typescript SDK theme={null}
  const res = await theo.code({
    prompt: "Write a TypeScript Express middleware for JWT authentication",
    language: "typescript",
    framework: "express",
  });

  console.log(res.content);    // Generated code
  console.log(res.artifacts);  // Any files created
  ```
</CodeGroup>

## Response

<ResponseField name="id" type="string">
  Unique code generation ID (prefixed `code_`).
</ResponseField>

<ResponseField name="created" type="string">
  ISO 8601 timestamp.
</ResponseField>

<ResponseField name="content" type="string">
  The generated code as text.
</ResponseField>

<ResponseField name="artifacts" type="object[]">
  Any files created during generation (e.g., multi-file outputs).
</ResponseField>

<ResponseField name="tools_used" type="object[]">
  Tools invoked during code generation.

  <Expandable title="Tool usage object">
    <ResponseField name="name" type="string">Tool name.</ResponseField>
    <ResponseField name="status" type="string">`"success"` or `"error"`.</ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="usage" type="object">
  <Expandable title="Usage object">
    <ResponseField name="cost_cents" type="number">Cost in cents.</ResponseField>
  </Expandable>
</ResponseField>

### Example Response

```json theme={null}
{
  "id": "code_abc123",
  "created": "2026-04-10T12:00:00Z",
  "content": "import { Request, Response, NextFunction } from 'express';\nimport jwt from 'jsonwebtoken';\n\nexport function authMiddleware(req: Request, res: Response, next: NextFunction) {\n  const token = req.headers.authorization?.split(' ')[1];\n  if (!token) return res.status(401).json({ error: 'No token provided' });\n  try {\n    const decoded = jwt.verify(token, process.env.JWT_SECRET!);\n    req.user = decoded;\n    next();\n  } catch {\n    return res.status(401).json({ error: 'Invalid token' });\n  }\n}",
  "artifacts": [],
  "tools_used": [],
  "usage": { "cost_cents": 0.05 }
}
```

## Errors

| Status | Code                  | Description                |
| ------ | --------------------- | -------------------------- |
| 400    | `missing_prompt`      | `prompt` is required       |
| 401    | `invalid_api_key`     | Missing or invalid API key |
| 429    | `rate_limit_exceeded` | Too many requests          |