Plans & Limits
CheapestInference sells unlimited time-block subscriptions on a model pool. Three pools are active: the Flagship Pool serves Kimi K3 (very limited seats), the Frontier Pool bundles Kimi K2.7 + GLM 5.2 + MiniMax M3, and the Core Pool bundles DeepSeek V4 Flash + MiMo v2.5. A subscription covers every model in its pool.
Your price is locked in
Section titled “Your price is locked in”The price you subscribe at is the price you keep, for as long as your subscription stays active. Whatever prices do, you always pay the lower line:
- Renewals never cost more. As long as you don’t cancel, your subscription renews at the price you signed up at — regardless of what new subscribers pay.
- Price drops reach you automatically. Pricing is dynamic, and when it moves down it moves down for everyone: if the current price of your subscription ever falls below what you’re paying, your renewal is charged at the lower price. You always pay the minimum of your contracted price and the current price — reductions are never reserved for new customers.
- Any increase would be strictly opt-in.* By default it is not possible for us to charge you more than your subscribed price: a renewal above it would require your explicit opt-in, and without it you will only ever be billed your price or less.
* In the unlikely event that circumstances entirely beyond our control were to make a general price increase unavoidable — a scenario contrary to the policy set out on this page — you would be notified by email well in advance, and no amount above your subscribed price would ever be charged without your explicit opt-in.
How pricing works — reserve daily time blocks
Section titled “How pricing works — reserve daily time blocks”The day is split into three 8-hour time blocks, aligned to global peak hours and shown in your local timezone. Reserve one, two, or all three blocks — all three gives full 24/7 coverage.
Flagship Pool — Kimi K3
Section titled “Flagship Pool — Kimi K3”| Block | Window (UTC) | Price |
|---|---|---|
| Asia-Pacific | 00:00 – 08:00 | $155/mo |
| Europe | 08:00 – 16:00 | $165/mo |
| Americas | 16:00 – 24:00 | $149/mo |
From $126.65/mo with annual billing (~15% off), available per block.
Core Pool — DeepSeek V4 Flash, MiMo v2.5
Section titled “Core Pool — DeepSeek V4 Flash, MiMo v2.5”| Block | Window (UTC) | Price |
|---|---|---|
| Asia-Pacific | 00:00 – 08:00 | $19.99/mo |
| Europe | 08:00 – 16:00 | $17.99/mo |
| Americas | 16:00 – 24:00 | $14.99/mo |
From $12.74/mo with annual billing (~15% off), available per block.
Frontier Pool — Kimi K2.7, GLM 5.2, MiniMax M3
Section titled “Frontier Pool — Kimi K2.7, GLM 5.2, MiniMax M3”| Block | Window (UTC) | Price |
|---|---|---|
| Asia-Pacific | 00:00 – 08:00 | $59/mo |
| Europe | 08:00 – 16:00 | $61/mo |
| Americas | 16:00 – 24:00 | $57/mo |
From $48.45/mo with annual billing (~15% off), available per block.
During your reserved hours, usage is truly unlimited — no tokens to count, no overage charges. Each key runs one request at a time — to run requests in parallel, create more keys (one per seat) or span several subscriptions with a combined key. Outside your reserved blocks, the key does not serve traffic.
- The authoritative source for live pricing and availability is the pool page: cheapestinference.com/pools.
- Full model lineup per pool, with per-model details: Models.
More pools via community pledges
Section titled “More pools via community pledges”Additional pools open through community pledges. Pledge for a model at cheapestinference.com/pools; when enough subscribers commit to a specific model, a new pool activates. See the Unlimited Subscriptions API for the full subscribe flow and response shapes.
Payment methods
Section titled “Payment methods”| Method | For |
|---|---|
| Card (Stripe) | Time-block subscriptions (monthly + annual) |
| USDC on Base | Subscriptions — temporarily paused |
| x402 | Agent subscriptions (no human setup needed) — temporarily paused |
Card subscriptions (Stripe) renew automatically each cycle (monthly or yearly) until you cancel — cancel anytime and access continues to the end of the paid period. USDC and x402 subscriptions are one-time (30 days, no auto-renewal) — you renew manually. Both are temporarily paused; card subscriptions are unaffected.
Concurrency
Section titled “Concurrency”Each key runs one request at a time during your reserved block. To run more requests in parallel — or to isolate clients — reserve additional seats and use one key each, or fold several subscriptions into a single combined key: where their hours overlap, parallel capacity stacks. Keys are independent, so one busy key never starves the others.