Public preview
Bill for LLM tokens Public preview
Learn how to bill for LLM tokens using Metronome.
You can use Metronome to bill for LLM token usage instead of building your own pricing system. Metronome allows you to implement usage-based billing to meter usage and generate invoices automatically.
Choose how to bill for LLM tokens:
| Approach | Best for |
|---|---|
| Resell LLM tokens | Platforms and gateways that give customers access to LLM providers and want to set their own markup on token costs. |
| Charge your app’s users | Apps that want to bill their own end users for AI feature consumption, such as token usage, API calls, or compute time. |
Resell LLM tokens
For new integrations, use Metronome to define your pricing and record usage. Stripe syncs model prices across providers, and you set your own margin. Send usage events directly to Metronome from your own integration.
Public preview
Billing for LLM tokens is in public preview and available to all users with a Metronome account. Create a Metronome account to get started.
Define your pricing model
In Metronome, define token-based products and rates, configure your markup, and combine usage charges with recurring fees or credits. Metronome evaluates usage in real time and sends invoices to Stripe for payment.
Automatic price updates
Stripe syncs token prices for OpenAI, Anthropic, and Google models, so your pricing always reflects current costs. When providers update their pricing or release new models we automatically apply new prices to all customers.
We’re actively expanding model support. If you need price tracking for models we don’t yet support, let us know at .
Supports any pricing model
- Usage-based : Bill customers only for the tokens they consume, with no fixed fee.
- Fixed fee with included usage : Charge a monthly fee that includes a set amount of token usage.
- AI credit packs and top-ups : Metronome natively supports custom pricing units. Define an “AI Credit,” configure how usage of each model converts to credits, and sell prepaid credit packs that customers can top up.
- Hybrid models : Combine any of the above approaches to create custom pricing tiers.
- Custom : Add your own usage-based rates alongside LLM token rates. Charge for custom models you’ve built or other non-LLM usage on the same Metronome rate card.
Track your AI usage
After you set up your pricing model, send usage events directly to Metronome. Include the customer, model, token type, and token count that Metronome uses to evaluate the applicable rate. You can meter tokens per customer, segmented by:
- Model (for example, GPT-5.6-sol, Claude Fable 5)
- Token type (input, output, and cached tokens for supported models)
Learn how to ingest events with Metronome.
Charge your app’s users
If you’re building an AI application and want to charge users for consumption, such as token usage, API calls, compute time, or AI feature access, Metronome provides real-time metering, flexible pricing, and automatic invoice generation without requiring you to resell LLM access.
Choose your billing model
| Model | Description | Best for |
|---|---|---|
| Per-token or per-unit metering | Track each unit of consumption (tokens, API calls, compute seconds) and bill based on total usage. | LLM wrappers, API marketplaces, inference platforms. |
| Tiered pricing | Offer usage tiers with different per-unit rates as volume increases. | Apps with free tiers and paid upgrades. |
| Subscription with metered overages | Charge a flat monthly fee that includes a usage allowance, then bill overages at a per-unit rate. | SaaS products with predictable base usage and variable AI features. |
Get started
To start onboarding:
- Sign up for Metronome .
- Follow the Metronome token billing guide to set up billing for LLM tokens.
If you have feedback, send it to .