MetricaOS

Glossary

Credit-Based Pricing

· · Leave a Comment

What is credit-based pricing?

Credit-based pricing is a pricing model where customers receive or buy a certain number of credits, and product usage consumes those credits.

In AI products, credits are often used to simplify complex usage. Instead of showing customers raw token counts, model costs, or provider pricing, the product gives them a simpler unit:

You have 10,000 AI credits this month.

Each AI action then uses a certain number of credits.

For example:

Generate a short reply: 5 credits

Summarize a document: 50 credits

Analyze a long report: 200 credits

Run an AI workflow: 500 credits

This makes pricing easier for customers to understand while still helping the company control usage and protect margins.

Why AI products use credit-based pricing

AI usage can be hard to explain.

Technical teams may understand tokens, model pricing, input costs, output costs, and provider invoices. But many customers do not want to think in those terms.

Customers usually want simpler answers:

How much usage is included?

How much have we used?

How much is left?

What happens if we need more?

Credit-based pricing gives them a clearer way to understand AI consumption.

It also gives the company flexibility. Different AI features can consume different numbers of credits based on cost, complexity, or customer value.

How credit-based pricing works

A product usually gives each plan a monthly credit allowance.

Example:

Starter: 2,000 AI credits/month

Pro: 20,000 AI credits/month

Business: 100,000 AI credits/month

When users perform AI actions, credits are deducted from the account.

Behind the scenes, the company may calculate credit usage based on:

Input tokens

Output tokens

Model used

Provider cost

Workflow complexity

Feature value

Desired margin

Plan type

The customer does not need to see all of this complexity. They only need to understand their credit balance and how credits are being used.

Credit-based pricing vs token-based billing

Credit-based pricing and token-based billing are related, but they are not the same.

Token-based billing measures or charges usage directly based on tokens.

Credit-based pricing converts usage into a product-specific credit system.

For example, instead of saying:

This action used 3,428 input tokens and 812 output tokens.

the product can say:

This action used 40 credits.

Internally, the company may still calculate those credits from token usage and model cost. Externally, customers see a simpler pricing unit.

This makes credit-based pricing useful for AI SaaS products where customers are business users rather than developers.

Benefits of credit-based pricing

Credit-based pricing has several benefits.

It makes pricing easier to explain. It helps customers understand how much usage they have left. It gives companies a way to set quotas, limits, prepaid usage, and overages.

It also helps protect gross margin. Expensive workflows can consume more credits, while cheaper workflows consume fewer.

This gives AI companies more control than unlimited usage, while still keeping pricing easier to understand than raw token billing.

Risks of credit-based pricing

Credit-based pricing can become confusing if credits feel arbitrary.

If customers do not understand why one action costs 10 credits and another costs 500, they may feel the system is unfair.

A good credit system should be simple, transparent, and connected to real product value.

Customers should be able to see:

Monthly credit allowance

Credits used

Credits remaining

Usage by feature

Billing period

What happens after credits run out

Without a usage dashboard, credit-based pricing can create confusion and support questions.

How MetricaOS helps

MetricaOS helps AI teams measure usage, attribute costs, and manage customer-level consumption.

Credit-based pricing only works when the underlying usage data is accurate. Teams need to know which customer used which feature, how many tokens were consumed, what it cost, and how many credits should be deducted.

MetricaOS gives AI product teams the metering foundation needed to design and manage credit-based pricing with more confidence.

Token Metering

· · Leave a Comment

What is token metering?

Token metering is the process of tracking how many tokens are used when someone interacts with a large language model.

In an AI product, every prompt sent to a model uses input tokens, and every response generated by the model uses output tokens. Token metering records this usage so companies can understand how much AI consumption is happening across customers, users, features, and models.

For example, if a customer uses an AI assistant to summarize a document, the system may track:

Customer: Acme Inc.

Feature: Document summary

Model: GPT-4.1

Input tokens: 3,200

Output tokens: 740

Total tokens: 3,940

This data helps the company understand usage, estimate cost, enforce limits, and prepare for usage-based pricing.

Why token metering matters

Token metering matters because LLM usage creates real cost.

Two customers may pay the same monthly subscription fee but use AI very differently. One customer may generate a few short replies. Another may process long documents, run workflows, or generate large reports.

Without token metering, both customers may look the same in your billing system. But their actual cost to serve may be very different.

Token metering helps AI teams answer questions like:

Which customers are using the most tokens?

Which features are driving the highest AI cost?

Which models are most expensive to operate?

Are free trial users consuming too much?

Should this usage count toward a quota or invoice?

For AI SaaS companies, token metering is not just a technical metric. It affects pricing, margins, customer profitability, and product decisions.

Input tokens vs output tokens

Token metering usually separates input tokens and output tokens.

Input tokens are the tokens sent into the model. These may include the user prompt, system prompt, conversation history, retrieved context, or uploaded document text.

Output tokens are the tokens generated by the model.

Both are important because many model providers price input and output tokens differently. A document analysis feature may have high input token usage, while a report generation feature may have high output token usage.

A good token metering setup should track both separately instead of only storing total tokens.

Token metering vs usage metering

Token metering is one type of AI usage metering.

Usage metering can include many different usage units, such as API calls, credits, documents processed, images generated, minutes transcribed, workflows completed, or storage used.

Token metering focuses specifically on token consumption in LLM-powered features.

For many AI products, token metering becomes the foundation for broader usage metering, cost tracking, quota management, and billing.

Common mistakes

A common mistake is tracking total token usage without customer attribution. This tells you how much AI was used overall, but not which customer caused the usage.

Another mistake is ignoring internal usage. Development, testing, demos, and admin actions can create token costs too. If those are mixed with customer usage, cost and margin analysis becomes inaccurate.

Teams also sometimes wait too long to add token metering. Once customers are already using the product, missing historical usage data can make pricing and billing decisions harder.

How MetricaOS helps

MetricaOS helps AI teams track usage across customers, users, models, and product features.

With token metering, teams can understand how much each customer consumes, which features create the most cost, and how token usage connects to pricing, quotas, and billing.

For AI products built on LLMs, token metering should be part of the foundation, not an afterthought.