Understand what people eat. Predict what happens next.
One API platform for personalized metabolic & nutrition intelligence
86%
Meal scan accuracy
+12.1
POINTS OVER FRONTIER LLMS
54M
Foods in our database
From meal to metabolic insight
One API supports the full journey. Take the full suite or just the piece you need
Capture what someone ate
Three ways in, one structured nutrition record out.
Meal Scan
One photo returns the dish, its foods, portions, and macros.
Food and barcode search
54M verified foods, brands, groceries, and restaurant dishes.
Natural-language logging
"A turkey sandwich with chips" becomes structured nutrition data.
Predict the metabolic response
Go beyond nutrition data with a predicted glucose response.
Device-free glucose predictions
A predicted 2-hour curve and impact read, no CGM required.
Turn it into a next action
Prediction matters when it changes what happens next.
Healthy food alternatives
Better next choices that respect allergies and preferences.
Personalized next actions
Guidance grounded in a person's own history and responses.
Most nutrition APIs stop at the food
Typical nutrition API
Meal Nutrition
January
Meal Nutrition Predicted glucose response Personalized next action
What you get back
Turn a meal photo into structured nutrition data
One photo scan returns the meal, its detected foods, and aggregated nutrition. Glucose predictions and healthier alternatives are separate calls on the same key
REST · JSON · API key auth
Predict how a meal will affect glucose before it’s eaten
No CGM, no finger sticks
- Two-hour predicted curve
- Low / medium / high impact read
- Patented prediction model built on millions of data points
Predicted response, chicken burrito bowl
Moderate impactThe world’s most accurate meal scanner
Evaluated across 1,000 real-world food images with human-reviewed annotations, diverse cuisines, realistic lighting and camera angles.
86%
Scan accuracy
Across ingredient recognition and macronutrient estimation, more than 12 accuracy points ahead of the next best app.
+12.1
Points over GPT-4o
Overall composite score of 86.24 versus 74.11 for GPT-4o on the same 1,000 images.
1,000
Benchmark images
Real meals from the January app, each with human-validated meal names, ingredients, and macros.
Lowest
Macro wMAPE
Weighted mean absolute percentage error on calories, carbs, protein, and fat, where lower is better.
The paper, the code, and the dataset are public, so you can rerun every number yourself before you sign anything.
Production-tested in the January app
The same capabilities power the January consumer app, where they are used every day for nutrition, weight, and glucose management
Glucose
49.7% → 57.4%
Time in healthy glucose range among people with type 2 diabetes.
Weight
74.4%
of participants lost weight while using the January app.
Diet
−16.7%
Sugar intake, the largest dietary shift observed in the cohort.
Start free. Make your first API call in minutes
Make your first API call
POST a meal photo, or GET a food search, over REST and read the JSON.
Move to production
Upgrade as volume grows.


SOC 2 Type II
Independently audited security controls.
HIPAA compliant
Access controls and audit trails throughout.
BAA available on Enterprise
For covered entities and their partners.
Plans
Start free, upgrade when you are ready
Free
Everything you need to try the API.
Pro
For teams shipping to production.
StartupComing soon
For pre-seed and seed-stage teams building toward production.
Enterprise
Volume pricing, enterprise SLAs, regulated health data security, and dedicated support.
See the full breakdown on the Pricing page.
Or ship the whole experience under your brand
If you would rather not build the front end, January can deliver the full app under your brand, configured to the capabilities you need
Start building with Nutrition Intelligence today.
Sign up free and make your first call in minutes