Credits, pricing, and spend limits

API usage is billed with prepaid credits, separate from the chat product subscription.

Welcome credit for paid plans

Every paying ISMS Copilot subscriber gets a one-time USD 10 API credit on the prepaid API balance. Paid chat plans only: the free plan and the no-card Plus trial do not include it. The credit is added automatically, usually right away and within a few hours of the first payment at the latest, so your first API call works before you buy a top-up. Existing paying subscribers receive it too, automatically. It is one per account, ever: it does not renew, and it does not expire.

The balance is visible at platform.ismscopilot.com/credits, where the ledger line is labelled "One-time API welcome credit".

How a top-up works

1. Open platform.ismscopilot.com/credits while signed in.
2. Choose an amount. The minimum top-up is USD 20.
3. Pay with card on Stripe.
4. Stripe sends you back to the Credits page on platform.ismscopilot.com. The new amount is on the balance as soon as payment completes.

This is not a chat plan upgrade. Chat subscriptions (Plus, Standard, Pro, Business) are billed in the chat app. After those card payments you return to chat.ismscopilot.com.

Each successful API completion then debits the prepaid balance. An empty balance returns a rate-limit / quota style error until you top up again.

Live unit rates (global vs EU paths) are shown in the console under Pricing. Treat the console as the source of truth for numbers; they can change without a docs deploy.

Per-key spend limits

On platform.ismscopilot.com/keys you can set optional caps per key for hour, day, week, or month. Use this to contain a leaked key or a runaway integration.

Request rate limit

Each API key can count on 120 requests per minute to POST /v1/chat/completions. Above that, the API may answer 429 with the OpenAI error code rate_limit_exceeded and a Retry-After header that says how many seconds to wait. The limit is counted on each API server, so a key can sometimes get through more than 120 in a minute; do not build on that. On a 429, the x-ratelimit-limit-requests, x-ratelimit-remaining-requests and x-ratelimit-reset-requests headers (OpenAI names) show the limit that applied to your key. The official OpenAI JavaScript and Python SDKs retry 429 responses by default. The limit protects every customer from a runaway client; if your integration needs more, contact us and we can raise it for your key.

Usage history

platform.ismscopilot.com/usage lists recent API calls and status for debugging (the old /history URL redirects there).

Relationship to other products