Try every Passio route on your own food, with real token costs.Get a free demo account →

Passio
Start building
PRICING

Know what it will cost before you build.

The period cap is included tokens plus purchased refills. Up to 10% over that cap is allowed. After that, calls return HTTP 429 until the next period or a refill. Auto-refill is on by default; turn it off in account settings to stop at the cap. Manual refills are purchased in the accounts portal.

Estimate your monthly costTry it free in the demo
Starter, where most teams begin
$99/month
  • 1M tokens a month
  • Refill $25 per 1M
  • Passio AI Studio
  • Email and Community Slack
Start building
Growth, when one app is live
$599/month
  • 5M tokens a month
  • Refill $10 per 1M
  • Per-request model switching
  • Usage insights
  • Dedicated Slack channel
Start building
Pro, for production traffic
$2,999/month
  • 100M tokens a month
  • Refill $2.50 per 1M
  • AI-powered insights
  • Enterprise support
Start building

Estimate your monthly cost

Tell us how many people use your app and what they do in it. Each row names the route. It starts on the model that route runs on today, and you can price another model from its test result or, when it hasn't been tested, from its price.

How many people use your app each month?

What will they use, and how often?

Start from:

The numbers are for an average active user, a few times a week, not someone who uses every feature every day. Change any of them to match your app.

  • ~5,857 tokens a use35M tokens a month
  • ~4,462 tokens a use45M tokens a month
  • ~75 tokens a use2.25M tokens a month
  • ~612 tokens a use
  • ~486 tokens a use
  • ~36,000 tokens a use
  • ~790,000 tokens a use
  • ~260,000 tokens a use
  • ~540,000 tokens a use
  • ~61,000 tokens a use
  • ~576 tokens a use
  • ~555 tokens a use2.22M tokens a month
Size of a use

Each AI row starts on the model that route runs on today. Accuracy is from Passio's test of that route, and a dash means the model wasn't tested. Tokens are the median production call over the 30 days to Nov 3, 2026 when the route has production traffic, the route test otherwise, and an estimate from the model's price when neither exists. Meal plans without production traffic yet use a rough, rounded-down figure from Passio's own test run of each plan type; each plan type is an EasyAI template you can tune for cost. Heavy is the 90th percentile. Starter always bills the default model. 30 uses a month is about once a day.

$1,399 a month on GrowthSee plans ↓

Plans renew monthly; refills are bought in 1M-token steps, and auto-refill is on by default. To measure your own calls, use a free demo account or read X-Billed-Tokens-Total on each response.

Tokens per call, by feature

Median billed tokens per call in production (30 days to Nov 3, 2026). A heavy call is the 90th percentile. "On other models" is the range across every model the route can run on, from the route's call size and each model's price. See models and test results to weigh accuracy against cost.

FeatureDefault modelTypical callHeavy callCalls per 1M tokensOn other models
Food logging
Photo meal logging
/napi/tools/vision/extractIngredientsAutoTyped
GPT-5.4 Nano5,8576,4931711,920 – 866,830
Photo logging with meal and ingredients
/napi/tools/vision/extractFoodAndIngredients
Gemini 3.5 Flash Lite10,03311,1471002,510 – 836,060
Photo logging, ingredients only
/napi/tools/vision/extractIngredients
GPT-5.4 Nano5,1005,5591962,300 – 765,070
Packaged product from a photo
/napi/tools/vision/extractPackagedProduct
GPT-5.4 Mini15,58716,139641,390 – 625,300
Text or voice meal logging
/napi/tools/extractIngredients
Gemini 3.1 Flash Lite4,4624,9362241,925 – 547,100
Edit a log by voice or text
/napi/tools/extractMealLogAction
Gemini 3.1 Flash Lite3,8074,0842631,160 – 462,140
Search and lookup
Food search, barcode or nutrition lookup (no AI)
No AI75—13,333—
Semantic food search (AI)
/napi/food/search/semantic
GPT-6 Luna1,1591,1928631,476 – 381,500
Search terms from a description
/napi/tools/generateSearchTerms
GPT-6 Luna1,1691,1998551,540 – 383,810
Guidance and ratings
Nutrition advisor message
/napi/tools/nutritionAdvisor
Gemini 3.1 Flash Lite6126991,634190 – 72,340
Rate a food against your criterion
/napi/tools/genericFoodRating
Gemini 3.1 Flash Lite4865552,058170 – 56,060
Ultra-processed food rating
/napi/tools/ultraProcessedFoodRating
Gemini 3.1 Flash Lite3,3913,903295660 – 398,210
Glycemic index and load
/napi/tools/estimateGlycemicIndexLoad
Gemini 3.1 Flash Lite7077751,414210 – 90,140
Hidden ingredients
/napi/tools/invisibleIngredientSuggestions
Gemini 3.1 Flash Lite5555801,802140 – 67,150
Possible ingredients
/napi/tools/possibleIngredientSuggestions
Gemini 3.1 Flash Lite4945382,024160 – 59,470
Alternatives to a food
/napi/tools/visualAlternativeSuggestions
Gemini 3.1 Flash Lite5766191,736180 – 69,410
Meal plans
Each plan type is an EasyAI workflow with a template in EasyAI. Start from it to change the steps, prompts or models, and tune the cost and the plans it writes for your app.
Meal plan, fast
/napi/tools/mealPlans/fast
Gemini 3.1 Flash Lite~36,000—~28—
Rough, from one Passio test run until production traffic is measured. A multi-step run, billed once.
Meal plan, macro-tuned
/napi/tools/mealPlans/macroTuned
Gemini 3.1 Pro Preview~790,000—~1—
Rough, from one Passio test run until production traffic is measured. A multi-step run, billed once.
Meal plan, budget
/napi/tools/mealPlans/budget
Gemini 3.5 Flash Lite~260,000—~4—
Rough, from one Passio test run until production traffic is measured. A multi-step run, billed once.
Meal plan, athletic
/napi/tools/mealPlans/athletic
Gemini 3.1 Pro Preview~540,000—~2—
Rough, from one Passio test run until production traffic is measured. A multi-step run, billed once.
Meal plan, family
/napi/tools/mealPlans/family
GPT-5.4 Mini~61,000—~16—
Rough, from one Passio test run until production traffic is measured. A multi-step run, billed once.
Passio AI Studio
Passio AI Studio workflow run
/sdk/chains/{chainId}/execute
Gemini 3.1 Flash Lite11,07415,504904,550 – 1,378,030
Other AI routes
Daily nutrition review
/napi/tools/dailyReview
Gemini 3.1 Flash Lite3,340—2991,150 – 400,800
From Passio's route test
Ingredient substitutes
/napi/tools/recipes/substitutes
Gemini 3.1 Flash Lite2,290—437790 – 274,800
From Passio's route test
Menu guidance
/napi/tools/menuCoach
Gemini 3.1 Flash Lite3,360—2981,150 – 403,200
From Passio's route test
Nutrition profile
/napi/tools/generateIntelligenceProfileHeader
Gemini 3.1 Flash Lite560—1,786190 – 67,200
From Passio's route test
Predicted ingredients
/napi/tools/predictIngredients
Gemini 3.1 Flash Lite2,230—448760 – 267,600
From Passio's route test
Recipe from a pantry
/napi/tools/recipes/fromPantry
Gemini 3.1 Flash Lite6,380—1572,190 – 765,600
From Passio's route test
Recipe makeover
/napi/tools/recipes/makeover
Gemini 3.1 Flash Lite6,360—1572,180 – 763,200
From Passio's route test
Recreate a dish
/napi/tools/recipes/recreateDish
Gemini 3.1 Flash Lite4,640—2161,590 – 556,800
From Passio's route test
Text and voice logging, meal and ingredients
/napi/tools/extractFoodAndIngredients
Gemini 3.1 Flash Lite4,160—2401,430 – 499,200
From Passio's route test

Tokens, refills, models

How do I sign up?
Choose a plan above and create an account. Your API key is created in the accounts portal, and the same account works for the REST API, the mobile SDKs and Passio AI Studio. Keep the key on your server.
Is every feature on every plan?
Yes. Every route is on every plan. Plans differ in included tokens, refill price, usage insights, and choosing the model per request, which needs Growth or Pro.
What else comes with a plan?
An EasyAI account with $10 of AI credit a month, on every plan. Use it to build what the standard routes don't cover, or your own version of one. EasyAI is the platform the Nutrition AI API runs on; Passio AI Studio is its nutrition workspace.
How many tokens does a plan include?
Starter includes 1M tokens a month. Growth includes 5M tokens a month. Pro includes 100M tokens a month.
What does a refill cost?
Starter refills at $25 per 1M. Growth refills at $10 per 1M. Pro refills at $2.50 per 1M.
What happens at the token cap?
The period cap is included tokens plus purchased refills. Up to 10% over that cap is allowed. After that, calls return HTTP 429 until the next period or a refill. Auto-refill is on by default; turn it off in account settings to stop at the cap. Manual refills are purchased in the accounts portal.
Which plans can switch models?
On Growth and Pro, choose the model per request. Automatic fallback applies, and the response names the model used. With Zero Data Retention on, routing is limited to the Vertex-hosted models named on the Trust page.
What is a token?
The unit every call is billed in. A call that uses AI is billed by the work the model did, so a photo on a large model uses more than a short text on a small one. Search, barcode and food lookups that use no AI are a flat 75 tokens.
How much does one call cost?
It depends on the route and the model. In production a text log is typically 2,000 to 5,000 tokens, a meal photo 5,000 to 20,000 depending on the model, and an advisor message a few hundred. The table below lists every route, measured on production traffic.
How do I see what a call costs?
Every response returns the tokens it used in the X-Billed-Tokens-Total header, and Growth and Pro show usage and projected spend per route. A free demo account shows the tokens for each call too.
Can I cap what a user costs?
Yes. Your application decides how often each feature runs, for example a daily limit on photo logs for free users. The calculator shows the cost per active user so you can set those limits.
Can I try it before paying?
Yes. A free demo account runs every route on your own photos and text for a limited time, with a daily token allowance, and shows what each call cost.

Enterprise

Enterprise uses these same token plans. There is no separate per-user price list. Contact Passio for a larger deployment.

Contact Passio

Live demo

Try every route on your own food, free.

The demo runs the real Nutrition AI API. Sign up, then photograph a meal, say what you ate, or search, and see what each call returns and costs.

Get a free demo accountSign in with your API key
  • A page for every route: photo, voice and text logging, search, barcode, the advisor, ratings, meal plans and shopping.
  • Switch the model on any route and see how the answer and the cost change.
  • See the exact request, response and tokens of every call.
  • Already a customer? Sign in with your API key; calls run on, and bill, your own account.