Token System and Pricing

Credit-Based Usage - The Nutrition AI platform uses a token-based usage model, where each API call consumes a specific number of tokens. Your subscription includes a monthly number of AI processing tokens.

Built for Scale - This usage-based model means you pay only for what your users actually use, allowing you to use the services as needed. You can even design your app's pricing around it (e.g. offer a free tier with limited daily tokens, then require an upgrade once a user exceeds their limit). In short, as your user base grows, the platform scales with you seamlessly.

Token Consumption - The usage figures provided in our documentation are estimates, as total token consumption depends on several factors, including image size and whether you are using a default or more advanced model.

Plans and tiers

Tier	Monthly	Included tokens	Refill (per 1M)	Easy AI	Insights	AI Insights	Model switching
Starter	$99	1M	$25	Yes	No	No	No
Growth	$599	5M	$10	Yes	Yes	No	Yes
Pro	$2,999	100M	$2.50	Yes	Yes	Yes	Yes

Feature descriptions:

• Easy AI — Access to the Easy AI platform to build custom no-code AI endpoints, chatbots, and workflows.

• Insights — Route-level usage analytics, cost breakdowns, and projected spend in your accounts dashboard.

• AI Insights — Advanced AI-powered analytics on your usage patterns and optimization recommendations.

• Model switching — Ability to choose which AI model (e.g. GPT-4.1 Mini, Gemini 2.5 Pro) is used per endpoint, either via the dashboard or per-request. See Model Settings.

Your token cap for the billing period is:

cap = (included_monthly_tokens + refill_tokens_this_cycle) × 1,000,000

Up to 10% over this cap is allowed (grace period) before requests are rejected. When you exceed the cap plus grace, API calls return 429 until the next period or until you add a refill. See Errors and Troubleshooting for details.

Refills - You can purchase additional tokens manually from the accounts portal (Manage Plan). Auto-refill can be enabled in your account settings so you never hit the cap unexpectedly.

Tracking Your Usage

There are three ways to monitor token consumption:

• Accounts Dashboard - Your accounts portal shows current and historic token usage, refill options, and a breakdown by route type.

• REST API Response Headers - Every API response includes headers like X-Budget-Cap, X-Period-Usage, X-Request-Usage, and X-Estimated-Cost-Usd for programmatic tracking. See Token Usage / Response Headers.

• SDK Token Budget Listener - The mobile SDKs provide a PassioAccountListener / PassioAccountDelegate that fires on each request with your current token budget, usage, and remaining capacity. See Track Token Usage (SDK).