FREEMODEL-AGNOSTICBRING YOUR OWN KEY

Snap. Bite. Done.

Free, model-agnostic AI nutrition tracking. Snap or describe a meal, and the AI model you choose returns estimated calories, macros, and portions — powered by affordable providers, especially Chinese LLMs.

// free on the chrome web store · bring your own key · your data stays yours

1,487 kcal
75% of 2,000
The whole loop

Three taps from plate to log.

The name is the workflow. No forms, no barcode hunting, no database of foods to search.

01 / SNAP

Capture the meal

Shoot a photo, paste an image from your clipboard, or just describe it in words. Whatever's fastest.

02 / READ

Your model reads it

The AI model you chose returns estimated calories, protein, carbs, and fat — with its assumptions and a confidence score. Edit anything before you keep it.

03 / DONE

Save to your day

It lands in your local log and updates your energy ring. Nothing left your device but that one call you asked for.

Under the hood

One model reads the plate. The result is structured for you.

SnapBite picks the cheapest suitable model for the task — a vision model for photos, a text model for descriptions — then turns the reply into a clean, editable breakdown.

Input

Photo or text

A meal photo, a pasted image, or a plain-text description of what you ate.

Vision or text model

Identify & estimate

The model you chose recognizes the food and estimates portions from what it can see or read.

Structured result

Your breakdown

Returned as an editable card you can correct and save.

caloriesmacrosingredientsassumptionsconfidence
Why it's different

Built to stay out of your way — and off your data.

Model-agnostic by design

No forced provider, no DeepSeek subscription. Speaks the OpenAI-compatible and Anthropic protocols, so nearly any model works — and model IDs and endpoints are editable when providers change names.

Cheapest suitable model

Affordable-first, with Chinese LLMs like Qwen-VL, DeepSeek, and Kimi (Moonshot) leading. Use a low-cost text model to describe, a vision model for photos — you pick what fits your budget.

Right model for the task

Photos need a vision-capable model; descriptions work with text models. SnapBite checks compatibility before it calls, so a text-only model on a photo gets a helpful nudge — not a silent failure.

Private by default

Every meal lives on your own device. No account, no backend, no telemetry — the only network request is the one you trigger, straight to your chosen provider.

Honest estimates

Everything is a visual estimate, never a medical measurement. SnapBite keeps its assumptions and a confidence score visible, and lets you correct any number before saving.

Open & featherweight

Free and MIT-licensed. Vanilla JavaScript, no framework, no build step — it opens instantly and stays out of your way.

One key, your choice

Pick a provider. Even one on your laptop.

SnapBite speaks the OpenAI-compatible and Anthropic protocols, so nearly any model works. Start at the top for the cheapest options — the starred picks are the Chinese-first recommended defaults.

ProviderBest forVisionGet a key
Qwen-VL ★ Chinese-first vision; trial quota Yes alibabacloud.com ↗
DeepSeek ★ Ultra-cheap text for the Describe tab Text only platform.deepseek.com ↗
Kimi (Moonshot) ★ Chinese-first, long-context; kimi-k3 reads photos & text Yes platform.moonshot.ai ↗
SiliconFlow Affordable vision + text models Yes cloud.siliconflow.cn ↗
OpenRouter One key, many providers & models Yes openrouter.ai/keys ↗
Google Gemini Fast models, generous free tier Yes aistudio.google.com ↗
OpenAI Reliable GPT-4o vision Yes platform.openai.com ↗
Claude Careful analysis with image support Yes console.anthropic.com ↗
Grok xAI vision where available Yes console.x.ai ↗
Ollama Local, offline & free on your own hardware Model-dependent ollama.com ↗
Custom Any OpenAI-compatible endpoint you run Model-dependent —

// ★ recommended defaults · prefer nothing leaves your device? run a local model with Ollama

One key is enough

You don't need every provider.

Choose a single provider, add its key in Settings, select a compatible model, and analyze your meal. That's it — no juggling accounts.

Choose the right model

Vision for photos, text for descriptions.

Photo mode needs a vision-capable model; Describe mode works with text models like DeepSeek. Model IDs and base URLs are editable, so you can update them whenever providers rename models or move endpoints.

What actually leaves your device

Almost nothing. And only when you say so.

SnapBite has no server of its own. There's nothing in the middle to log your meals, sell your habits, or hold your history hostage. Here's the entire data map.

Your meal photo or text
→ your provider
Your API key
stays local
Your meal history & totals
stays local
Usage analytics
don't exist
Questions

SnapBite FAQ

Quick answers about the free AI calorie counter, supported models, privacy, and accuracy.

Is SnapBite free?

Yes. SnapBite is free and open source (MIT licensed). You bring your own AI API key, so the only cost is your chosen provider's usage — often a fraction of a cent per photo, and several providers (like Qwen, Gemini, and SiliconFlow) have free tiers.

How does SnapBite count calories from a photo?

Snap or paste a food photo and a vision AI model you choose identifies the foods, estimates the portions, and returns calories plus protein, carbs, and fat — with its assumptions and a confidence score. You can edit any number before saving it to your daily log. Prefer typing? The Describe tab estimates calories from a text description instead.

Which AI models does SnapBite support?

DeepSeek, Qwen-VL, Kimi (Moonshot), SiliconFlow, OpenRouter, Google Gemini, OpenAI, Claude, and xAI Grok — or a fully local model via Ollama. Model IDs and endpoints are editable, so you're never stuck when providers rename models. Chinese-first models like Qwen-VL, DeepSeek, and Kimi are the affordable defaults.

Do I need an account to use SnapBite?

No sign-up and no account. You paste your own API key once, and your meal log lives locally on your device.

Is my nutrition data private?

Yes. SnapBite has no servers and no analytics. Your meals stay on your device, and the only data that leaves is the photo or text you choose to analyze, sent directly to the AI provider you configured. With a local model via Ollama, nothing leaves your device at all.

Which browsers does SnapBite work in?

Any Chromium browser that supports Manifest V3 — Chrome, Edge, Brave, and Arc.

Are the calorie and macro numbers accurate?

They're visual estimates, not medical measurements. SnapBite keeps its assumptions and a confidence score visible and lets you correct any value before saving. It isn't medical advice.

Snap. Bite. Done.

Free on the Chrome Web Store — model-agnostic, open source, and yours to fork. Add it to Chrome and bring your own key.