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 URIYour 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 FlashThe 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 + ZodThe 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 → UIThe 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 doSee it in action
Upload any food photo and watch Gemini 2.5 Flash build the recipe in real time.
Try It Free10 free credits · No credit card required