ChefAI Logo
Built on Gemini 2.5 Flash

How ChefAI Works

ChefAI is built on top of Gemini 2.5 Flash, Google's multimodal AI model, orchestrated through Genkit to turn a food photo into a structured, validated recipe in seconds.

The AI pipeline

Four stages turn a raw image into a recipe your kitchen can actually use.

Image ingestion

Base64-encoded data URI

Your photo is encoded as a Base64 data URI and passed directly to the model alongside the prompt. No external image hosting is required.

Vision analysis

Gemini 2.5 Flash

The raw pixel data is handed to Gemini 2.5 Flash, which identifies the dish, infers ingredients, estimates cooking method, and assesses difficulty — the foundation ChefAI is built on.

Schema enforcement

Google Genkit + Zod

The model output is constrained to a strict Zod schema via Google Genkit. This guarantees a consistent structure — no free-form text, no missing fields.

Validated output

Typed JSON → UI

The validated JSON is returned to the client: recipe name, ingredient list, numbered instructions, calorie estimate, prep time, and difficulty enum (Easy / Medium / Hard).

Technical specs

Model

Gemini 2.5 Flash

Provider

Google AI

Framework

Google Genkit

Output

Structured JSON

Encoding

Base64 Data URI

Schema

Zod (strict)

From recipe to routine

Once Gemini hands back a structured recipe, it's yours — save it, organize it into collections, and drop it into a weekly meal plan.

See everything ChefAI can do

See it in action

Upload any food photo and watch Gemini 2.5 Flash build the recipe in real time.

Try It Free

10 free credits · No credit card required