Pricing

You pay the model's upstream list price plus 15%, and nothing else. No subscription, no seat fee, no charge for keys or logs.

TokensUpstream list price plus 15%
Sub-keysUnlimited, free
Request logs90 days, free
Minimum top-up$10
SubscriptionNone
Seat feeNone

How the margin works

Every model carries the price its upstream provider charges, plus 15%. That is the whole pricing model. The per-model figures on the models page already include the margin, so the price you read there is the price you are billed, per million tokens, in and out.

Billing is in whole nano-dollars, a billionth of a dollar, so short calls are costed exactly rather than rounded up into a bigger number.

Spend caps are part of the price

Every key can carry a lifetime cap, a monthly cap, or both. Redline reserves the worst-case cost of a request before it leaves and clamps the response length to what the cap covers, so a key cannot bill past the number you set on it. A request that will not fit under the cap is refused instead of sent.

That matters most for agents: something looping overnight is bounded by its key, not by your whole balance. The mechanics are on the spend caps page.

What is not charged Keys, spend caps, the request log and the signed receipts are all free. The only line on the bill is tokens.

Live per-model prices

Prices differ by model, from a few cents per million tokens to several dollars. The models page lists every model reachable through one key with its context length and its price, and the catalogue is synced from upstream regularly. Point your client at https://redline-gateway.pages.dev/v1 and the model id decides the cost.

FAQ

Is there a subscription?

No. There is no subscription, no seat fee and no monthly minimum. You buy credit and spend it on tokens.

Do the prices on the models page include the margin?

Yes. The per-model prices are what you pay, with the 15% already added, so the number you read is the number you are billed.

Do extra API keys cost anything?

No. Sub-keys are unlimited and free. Mint one per engagement, per client or per script and revoke it when the job ends.

What is the minimum top-up?

Ten dollars. After the first top-up there is no minimum spend.

How long are request logs kept?

Ninety days, at no cost. The log holds the model, token counts, cost, latency and outcome. It never holds the prompt or the completion.

Next