API Endpoint

POST Email Classification API

/api/v1/ai/email-classification

Automatically categorize incoming emails to route them to correct departments and detect urgency.

Request Body Parameters

Field	Type	Required	Description
`email_content`	string	Required	The main body of the email to classify (Max: 10,000 characters).
`subject`	string	Optional	Optional email subject line. Providing this increases classification accuracy.
`allowed_categories`	array of strings	Optional	Optional strict list of allowed categories (e.g., ["sales", "support", "billing"]). If provided, the AI will force the email into one of these buckets.
`detect_urgency`	boolean	Optional	Optional. If true, the AI will evaluate the email and return an urgency level (low, medium, high, critical). Default is false.
`extract_schema`	object	Optional	Optional schema definition (JSON object) of exact data points you want extracted from the email. Example: {"order_number":"string", "refund_amount":"number"}
`custom_instructions`	string	Optional	Optional specific rules to guide the data extraction process.
`model`	string	Optional	Optional AI model to use.

Example Request (Dynamic Routing)

In this example, we provide the allowed_categories array. The AI guarantees the category will match one of these options perfectly, allowing you to easily write if/else statements in your codebase.

JSON Request

{
  "subject": "Double charged on my last invoice!",
  "email_content": "Hello, I was looking at my bank statement and I was charged twice for my Pro subscription this month. Please refund one of the charges immediately as this is unacceptable.",
  "allowed_categories": ["sales", "support", "billing", "spam"],
  "detect_urgency": true
}

cURL

curl -X POST https://rsflowhub.com/api/v1/ai/email-classification \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "subject": "Double charged on my last invoice!",
    "email_content": "Hello, I was looking at my bank statement and I was charged twice for my Pro subscription this month. Please refund one of the charges immediately as this is unacceptable.",
    "allowed_categories": ["sales", "support", "billing", "spam"],
    "detect_urgency": true
  }'

Example Response

The API processes the email and outputs the category and urgency level.

JSON Response

{
  "success": true,
  "data": {
    "result": {
      "category": "billing",
      "confidence": 0.98,
      "urgency": "high"
    }
  },
  "meta": {
    "credits_used": 2,
    "credits_remaining": 997
  }
}

Advanced: Classification + Data Extraction

This endpoint allows you to simultaneously classify the email AND extract strictly typed data by providing an extract_schema. The credit cost will adjust automatically based on the length of the email and extracted data.

JSON Request

{
  "subject": "Cancel order #88492 immediately",
  "email_content": "I placed an order yesterday for the standard plan, but I changed my mind. Please cancel it and refund the $49.00 back to my card ending in 4421.",
  "allowed_categories": ["sales", "support", "billing"],
  "detect_urgency": true,
  "extract_schema": {
    "order_number": "string",
    "requested_action": "string",
    "refund_amount_cents": "integer",
    "card_last_four": "string"
  },
  "custom_instructions": "Convert all refund amounts into cents (e.g. 49.00 becomes 4900)."
}

JSON Response

{
  "success": true,
  "data": {
    "result": {
      "category": "billing",
      "confidence": 0.99,
      "urgency": "high",
      "extracted_data": {
        "order_number": "88492",
        "requested_action": "cancel and refund",
        "refund_amount_cents": 4900,
        "card_last_four": "4421"
      }
    }
  },
  "meta": {
    "credits_used": 3,
    "credits_remaining": 994
  }
}

API Request Example

Use the cURL snippet below to test the endpoint.