Billing model
ZeroFA uses a prepaid wallet with real-time usage billing. After funding it, charges are calculated from upstream tokens, images, and other usage at the model list price, then deducted from your Wallet in real time.
- Currency: configured currency, settled from actual usage in real time
- Failed requests are not charged (zero cost)
- If a stream disconnects early, generated tokens are still billed
- Prompt-cache hits are billed at the discounted cache_read rate
Top up
Fund your Wallet with Alipay, WeChat Pay, or USDT-TRC20. Funds are available after confirmation. The API wallet is separate from web chat subscriptions.
Rate limits
Each API key can have an independent total budget, RPM limit, and daily request limit. Configure them when creating or editing a key in API Keys. TPM is not currently enforced, and responses do not include X-RateLimit-Remaining-* headers.
Prices
See live per-model input, output, per-image, and per-second prices in the Model Catalog. Capabilities and prices update automatically as models are added.
Track costs
- Aggregated statistics: Spend Analysis
- Individual calls: Usage Logs
- Wallet transactions: Wallet
- API: the cost_usd field from GET /api/me/usage/summary