Skip to main content
POST
/
api
/
parseRecipeFromImage
Parse Recipe from Image
curl --request POST \
  --url https://api.example.com/api/parseRecipeFromImage \
  --header 'Content-Type: application/json' \
  --data '{}'
{
  "success": true,
  "title": "<string>",
  "ingredients": [
    {
      "groupName": "<string>",
      "ingredients": [
        {
          "amount": "<string>",
          "units": "<string>",
          "ingredient": "<string>"
        }
      ]
    }
  ],
  "instructions": [
    {}
  ],
  "summary": "<string>",
  "author": "<string>",
  "cuisine": [
    {}
  ],
  "servings": "<string>",
  "prepTimeMinutes": 123,
  "cookTimeMinutes": 123,
  "totalTimeMinutes": 123,
  "imageData": "<string>",
  "imageFilename": "<string>",
  "error": {
    "code": "<string>",
    "message": "<string>",
    "retryAfter": 123
  }
}

​
Overview

The /api/parseRecipeFromImage endpoint accepts image uploads (recipe cards, cookbook pages, screenshots) and uses AI vision models to extract recipe data from the image. Supported formats: JPG, PNG, WEBP, GIF Maximum file size: 10MB

​
Request

This endpoint accepts multipart/form-data requests with an image file.
​
image
file
required
Image file containing a recipe. Supported formats: JPG, PNG, WEBP, GIF.Maximum file size: 10MB

​
Response

​
Success Response

​
success
boolean
required
Always true for successful responses
​
title
string
required
The recipe title extracted from the image
​
ingredients
array
required
Array of ingredient groups. Each group contains a groupName and an array of ingredients.
​
instructions
array
required
Array of cooking instruction steps as strings
​
summary
string
AI-generated recipe summary
​
author
string
Recipe author name (if visible in the image)
​
cuisine
array
Array of cuisine tags (e.g., ["Italian", "Mediterranean"])
​
servings
string
Number of servings or yield (e.g., “4 servings”, “12 cookies”)
​
prepTimeMinutes
number
Preparation time in minutes (if visible in the image)
​
cookTimeMinutes
number
Cooking time in minutes (if visible in the image)
​
totalTimeMinutes
number
Total time in minutes (prep + cook)
​
imageData
string
Base64-encoded data URL of the uploaded image for preview purposes
​
imageFilename
string
Original filename of the uploaded image

​
Error Response

​
success
boolean
Always false for error responses
​
error
object
Error details

​
Error Codes

​
ERR_INVALID_URL
No image file provided or invalid file type. Despite the code name, this is used for file validation errors.
​
ERR_NO_RECIPE_FOUND
No recipe found in image - could not read recipe text
​
ERR_AI_PARSE_FAILED
Failed to extract recipe from image or AI service not configured
​
ERR_RATE_LIMIT
Too many requests - rate limit exceeded
​
ERR_UNKNOWN
An unexpected error occurred

​
Examples

curl -X POST https://your-domain.com/api/parseRecipeFromImage \
  -H "Content-Type: multipart/form-data" \
  -F "[email protected]"

​
Success Response Example

{
  "success": true,
  "title": "Grandma's Chocolate Cake",
  "ingredients": [
    {
      "groupName": "For the cake",
      "ingredients": [
        {
          "amount": "2",
          "units": "cups",
          "ingredient": "all-purpose flour"
        },
        {
          "amount": "1 3/4",
          "units": "cups",
          "ingredient": "granulated sugar"
        }
      ]
    }
  ],
  "instructions": [
    "Preheat oven to 350°F.",
    "Mix flour and sugar in a large bowl.",
    "Bake for 30-35 minutes."
  ],
  "summary": "A classic chocolate cake recipe with rich, moist layers.",
  "author": "Grandma Smith",
  "servings": "12 servings",
  "prepTimeMinutes": 20,
  "cookTimeMinutes": 35,
  "totalTimeMinutes": 55,
  "imageData": "data:image/jpeg;base64,/9j/4AAQSkZJRg...",
  "imageFilename": "recipe-card.jpg"
}

​
Error Response Example

{
  "success": false,
  "error": {
    "code": "ERR_INVALID_URL",
    "message": "Invalid file type. Please upload a JPG, PNG, WEBP, or GIF image."
  }
}
This endpoint uses AI vision models and may consume significant API tokens. Rate limits apply.
Images must be clear and readable for best results. Low-resolution or blurry images may result in parsing errors.

Build docs developers (and LLMs) love

Get started for freeTalk to us