{
"dish": {
"name": "Nutella",
"allergens": [
"milk",
"soy"
],
"diet_compat": {
"vegan": "no",
"plantbased": "no",
"vegetarian": "yes",
"flexitarian": "yes",
"pescatarian": "yes"
},
"ingredient_count": 1,
"total_metric_amount": 100,
"total_nutritional_content": {
"fat": 30.9,
"iron": 2.7,
"zinc": 0,
"fiber": 2.7,
"sugar": 56.76,
"folate": 0,
"niacin": 0,
"sodium": 41.08,
"calcium": 108.11,
"omega_3": 0,
"protein": 6.3,
"calories": 539,
"magnesium": 0,
"potassium": 458.92,
"trans_fat": 0,
"vitamin_a": 0,
"vitamin_c": 0,
"vitamin_d": 0,
"vitamin_e": 0,
"vitamin_k": 0,
"vitamin_b6": 0,
"cholesterol": 14.05,
"vitamin_b12": 0,
"carbohydrate": 57.5,
"saturated_fat": 10.81,
"monounsaturated_fat": 0,
"polyunsaturated_fat": 0
}
},
"billing": {
"price_usd": 0.05,
"billable_unit": "credits",
"unit_cost_usd": 0.01,
"billable_units": 5
},
"food_response": [
{
"food": {
"food_id": "0",
"servings": {
"serving": [
{
"fat": 5.72,
"iron": 0.5,
"zinc": 0,
"fiber": 0.5,
"sugar": 10.5,
"folate": 0,
"niacin": 0,
"sodium": 7.6,
"calcium": 20,
"omega_3": 0,
"protein": 1.17,
"calories": 100,
"magnesium": 0,
"potassium": 84.9,
"trans_fat": 0,
"vitamin_a": 0,
"vitamin_c": 0,
"vitamin_d": 0,
"vitamin_e": 0,
"vitamin_k": 0,
"is_default": true,
"serving_id": "0",
"vitamin_b6": 0,
"cholesterol": 2.6,
"vitamin_b12": 0,
"carbohydrate": 10.64,
"saturated_fat": 2,
"metric_serving_unit": "tbsp",
"monounsaturated_fat": 0,
"polyunsaturated_fat": 0,
"serving_description": "2 tbsp",
"metric_serving_amount": 18.5,
"measurement_description": "tbsp"
}
]
},
"food_name": "Nutella",
"food_type": "Generic"
},
"eaten": {
"unit": null,
"count": null,
"units": 1,
"unit_count": 2,
"unit_grams": 18.5,
"per_unit_grams": null,
"metric_description": "tbsp",
"total_metric_amount": 37,
"singular_description": "serving",
"per_unit_metric_amount": 37,
"total_nutritional_content": {
"fat": 11.43,
"iron": 1,
"zinc": 0,
"fiber": 1,
"sugar": 21,
"folate": 0,
"niacin": 0,
"sodium": 15.2,
"calcium": 40,
"omega_3": 0,
"protein": 2.33,
"calories": 199,
"magnesium": 0,
"potassium": 169.8,
"trans_fat": 0,
"vitamin_a": 0,
"vitamin_c": 0,
"vitamin_d": 0,
"vitamin_e": 0,
"vitamin_k": 0,
"vitamin_b6": 0,
"cholesterol": 5.2,
"vitamin_b12": 0,
"carbohydrate": 21.28,
"saturated_fat": 4,
"monounsaturated_fat": 0,
"polyunsaturated_fat": 0
}
},
"food_id": 0,
"allergens": [
"milk",
"soy"
],
"food_name": {
"de": "Nutella",
"en": "Nutella",
"fr": "Nutella",
"it": "Nutella",
"tr": "Nutella"
},
"diet_compat": {
"vegan": "no",
"plantbased": "no",
"vegetarian": "yes",
"flexitarian": "yes",
"pescatarian": "yes"
},
"match_score": null,
"suggested_serving": {
"serving_id": 0,
"number_of_units": "2",
"metric_serving_unit": "tbsp",
"serving_description": "2 tbsp",
"metric_measure_amount": 18.5,
"metric_serving_description": "tbsp"
}
}
]
}Nutriscan Barcode Lookup API
Nutriscan Barcode Lookup finds branded food nutrition from a barcode, returning product nutrition, diet compatibility, and detected allergens.
- Runtime (p50)
- 1m
- Estimated price
- Usage-based
Overview
NutriScan | Barcode Lookup Overview
NutriScan | Barcode Lookup is a byterise text-to-text model designed to turn a food barcode into structured nutrition information. It solves a practical problem for apps that need fast product lookup without manual entry: users scan a barcode, and the model returns product nutrition, diet compatibility, allergens, and provider billing details. Within the NutriScan family, the main differentiator is its focus on barcode-based food intelligence rather than general-purpose text generation. In each::labs workflows, NutriScan | Barcode Lookup is best suited for structured nutrition retrieval, catalog enrichment, and consumer-facing food transparency features. Because the available research results do not expose a public spec sheet, the safest interpretation is that this model is optimized for text input and text output around product identifiers rather than images or video.
Capabilities
Capabilities
- Looks up branded food products from a barcode.
- Returns product nutrition in text form for downstream apps.
- Identifies diet compatibility for product filtering and recommendation flows.
- Surfaces allergen information for safety and label-aware experiences.
- Provides provider billing details for platform-side accounting workflows.
- Supports structured text responses that are easier to parse than open-ended chat output.
- Fits catalog enrichment, food logging, and consumer lookup interfaces.
- Works as a focused NutriScan | Barcode Lookup API component inside byterise text-to-text pipelines.
Use cases
Use Cases for NutriScan | Barcode Lookup
A nutrition app developer can use NutriScan | Barcode Lookup to turn scanned UPCs into product facts for a food diary. A useful prompt would be,
Look up this barcode and return calories, macros, allergens, and diet compatibility.
A creator building meal-planning content can use the model to verify packaged foods before publishing ingredient or allergy notes. A practical prompt is,
Summarize this barcode lookup for a recipe card with concise nutrition and allergen text.
A marketer managing a grocery catalog can use the model’s structured product nutrition output to enrich product pages at scale. A good prompt is,
Return a clean product metadata block from this barcode for catalog use.
A developer integrating billing workflows can use the provider billing fields to connect scan events to internal usage records. A prompt example is,
Extract the billing-relevant fields from this barcode lookup response.
Tips & tricks
Tips and Tricks
For the best results, send a clean barcode value and keep the request narrowly scoped. If your workflow supports optional fields, include product-region context so the lookup can align with the correct market listing. Use short, explicit instructions for the output shape, such as JSON-like fields or a fixed label order, so downstream systems can parse responses reliably. In a NutriScan | Barcode Lookup API integration, minimize extra natural-language chatter unless you need transformation or normalization. Example prompts include:
Look up this barcode and return nutrition facts, allergens, and diet compatibility.
Return a concise product summary for this barcode in structured text.
Extract provider billing details from this barcode lookup result.
This kind of tight prompting helps byterise text-to-text systems stay consistent.Technical spec
Technical Specifications
- Model type: text-to-text, within the byterise text-to-text family.
- Primary input: barcode or barcode-derived product query, plus any optional lookup context provided by the caller.
- Primary output: structured text covering product nutrition, diet compatibility, allergens, and billing-related fields.
- Input format: text.
- Output format: text.
- Resolution support: not applicable from the available information.
- Max duration / aspect ratio: not applicable for this text-to-text model.
- Processing time: not publicly verified in the available research; treat latency as implementation-dependent in the NutriScan | Barcode Lookup API.
- Architecture details: not publicly disclosed in the available research.
Things to be aware of
Things to Be Aware Of
NutriScan | Barcode Lookup depends on the quality of the barcode input and the completeness of the underlying product record. If the barcode is damaged, invalid, region-specific, or not recognized, results may be incomplete. Users often make the mistake of sending broad natural-language requests when a precise barcode lookup is all that is needed. Another common issue is expecting image reading behavior from a text-to-text model. In each::labs integrations, keep the request payload small, validate the barcode before calling the NutriScan | Barcode Lookup API, and design for occasional missing fields in nutrition or allergen data.
Important NoticeNutriScan provides AI-generated nutritional analysis for informational purposes only.
- Nutritional values, allergen detection, ingredient measurements, and dietary compatibility results are estimates and may be incomplete or inaccurate.
- Outputs must not be considered medical advice, diagnosis, or treatment recommendations.
- The API must not be used as the sole basis for determining whether food is safe for consumption or suitable for individuals with allergies or medical conditions.
- Users are solely responsible for independently reviewing and verifying all outputs before making dietary or health-related decisions.
- Human verification is strongly recommended for all health and safety-related use cases.
AI model outputs are probabilistic in nature and may contain inaccuracies. Neither Eachlabs nor the model provider guarantees the accuracy or completeness of any output.
Key considerations
Key Considerations
NutriScan | Barcode Lookup is most useful when your product experience depends on structured food data rather than free-form answers. It works best when the barcode is accurate and the catalog behind the lookup is current. For teams building food apps, diet assistants, or retail utilities, the model can reduce manual nutrition entry and support consistent product enrichment. If you need visual interpretation of packaging, this model is not the right fit because the documented behavior centers on text lookup. The best value comes from using the NutriScan | Barcode Lookup API in workflows where speed, consistency, and structured output matter more than open-ended language generation.
Limitations
Limitations
This model is specialized, not general-purpose. It is built for barcode-based product lookup and does not have documented support for image, video, or multimodal input. The available research does not confirm public benchmarks, latency guarantees, or architecture details. It may also return partial results when product data is missing or inconsistent. For workflows that require visual packaging recognition, broad reasoning, or long-form content generation, NutriScan | Barcode Lookup is not the right tool.
Related models
4 models
About Nutriscan Barcode Lookup API
What is NutriScan Barcode Lookup?
NutriScan Barcode Lookup identifies a branded, packaged food from its barcode and returns the matching nutrition data. You get product nutrition facts, diet compatibility, and detected allergens in a structured response, which makes it quick to log or display a known product. Results are AI-generated for informational use.