# Credits

> How the prepaid balance works, what draws it down, and how to avoid running dry mid-run.

_Source: https://aiprimetech.io/docs/billing/credits/ · Home > Docs > Billing_

Credits are a prepaid balance spent per token. Every request deducts input and output tokens at that model's rate.

- **Rate:** **$13 = $100** in credits
- **Expiry:** None
- **Shared across models:** Yes — one balance for Claude, GPT, Gemini and MiniMax
- **Runs out:** Requests return `402` until you top up


## What draws the balance down

- **Input tokens** — the whole request: system prompt, full history, tool schemas, images.
- **Output tokens** — what the model generates, at 4–5× the input rate.
- Nothing else. There is no per-request fee and no monthly minimum.


## Reading your usage

Every response carries a `usage` object with exact token counts — that is the billing basis, and it is worth logging alongside your own request ids. The dashboard aggregates the same data per model and per key.


## Not running out mid-task

- Long agent runs consume credits faster than chat because history is resent every turn.
- A `402` mid-session stops work immediately — top up before a long run rather than during one.
- If usage is steady and heavy, a [plan](/docs/billing/plans/) is usually cheaper than credits.

> Crypto top-ups currently carry +25%, and a new account's first crypto top-up carries +100%. Both are applied automatically at checkout.

- [Pricing](https://aiprimetech.io/docs/billing/pricing/) — Rates and conversion
- [Top up](https://aiprimetech.io/topup/) — Add credits
- [Cost control](https://aiprimetech.io/docs/guides/cost-control/) — Make credits last


---
_ClaudeAPIKey.dev is an independently operated, Anthropic-compatible API gateway. Not affiliated with Anthropic._