Billing & Costs - OpenModex

How Billing Works

OpenModex uses a pay-as-you-go model. You’re billed based on:

Input tokens — the tokens in your prompt/messages
Output tokens — the tokens generated by the model
Model pricing — each model has its own per-token rate

Pricing

OpenModex passes through provider pricing with transparent margins. View current pricing:

Pricing page
Models API — includes pricing per model

Cost Tracking

Every response includes cost information:

{
  "usage": {
    "prompt_tokens": 150,
    "completion_tokens": 50,
    "total_tokens": 200,
    "cost_usd": 0.001
  }
}

Dashboard Analytics

The dashboard provides:

Real-time spending — current balance and burn rate
Per-model breakdown — cost and usage by model
Daily trends — spending over time
Per-key analytics — track costs by API key

Saving Money

Use cost-optimized routing — let OpenModex pick the cheapest model
Enable caching — avoid paying for repeated queries
Choose smaller models — gpt-4o-mini is 10x cheaper than gpt-4o
Set max_tokens — limit output length to control costs
Use BYOK — bring your own provider keys for volume discounts

Balance & Payments

Add funds via credit card (Stripe) or cryptocurrency
View balance and transaction history in the dashboard
Set up low-balance alerts to avoid service interruption