Wholesale LLM API: plan volume spending with a wallet and key budgets
Router One does not publish self-serve wholesale or volume discount tiers. Start with the per-model catalog rates, then use the settled request charge to check any applicable account/model discount and plan multiplier. FX and payment-channel fees are shown separately at checkout. Pricing starts as low as 10% of official provider list prices (up to 90% off) on select models; live per-model rates: https://router.one/models. Volume buyers can organize spending with one funded wallet, one budget-capped key per workload or customer, and per-request usage data for reconciliation.
Catalog rates and settled charges
The /models page publishes model rates before you top up. Those rates are a starting point, not a promise that every account's final charge is identical. Applicable account/model discounts and plan multipliers affect settlement; the recorded total already includes them. Check the settled amount and available pricing details in Dashboard → Logs, and do not infer a volume discount from the size of a top-up.
How volume buyers structure spend
- Fund one wallet — card or Alipay through the hosted checkout, or USDT/USDC on six chains
- Issue one API key per workload, customer, or resold tier, used server-side in your service, each with its own maxSpend budget on wallet charges; rate limits follow platform defaults and can be raised on request
- Reconcile from per-request usage data: model, tokens, cost, latency, status on every call
- Reselling? Your customer pricing and margin live in your own portal — see the reseller guide
Posted rates vs a negotiated wholesale deal
| Dimension | Router One posted rates | Negotiated wholesale deals |
|---|---|---|
| Price transparency | Per-model rates published on /models before you pay | Quoted privately after a sales process |
| Volume commitment | None — top up what you need and check settled wallet charges | Usually a prepay or committed-volume contract |
| Time to start | Create a key and call the endpoint today | Days to weeks of negotiation |
| Spend control | maxSpend budget and expiry per key | Contract-level, enforced after the fact |
| Fit for very large committed volume | Catalog rates and applicable pricing; no published self-serve volume tiers | A negotiated contract can win at very large scale |
Metering resale volume without sub-accounts
Router One has no sub-accounts or wholesale console — keys are the unit of structure. Give every downstream customer, tier, or internal workload its own key, used server-side in the service you run, with its own maxSpend budget on wallet charges (plan-covered requests do not count toward it); request and token rate limits follow platform defaults and can be raised on request. Dashboard → Logs filters by model, API key, status and date range; the API key column (and the request detail) names the key that sent each request — web-console calls are labeled as such. Dashboard → Usage ranks your API keys by wallet charges, tokens and requests for the chosen range, and each key links to its own logs. Logs (current filters) and the wallet ledger (chosen range) export to CSV. For attribution below key level — per end customer or run on a shared key — keep your own labels and request IDs in your application.
Not provided today (plan around these)
- Published self-serve wholesale or volume discount tiers
- Sub-accounts / child accounts
- White-label branding
- Configurable markup multipliers — your margin is set in your own portal
FAQ
Do you offer wholesale or volume discounts?
There are no published self-serve wholesale or volume discount tiers. A larger top-up does not establish a discount; check the settled wallet charge and any applicable account/model discount or plan multiplier in Logs. Pricing starts as low as 10% of official provider list prices (up to 90% off) on select models; live per-model rates: https://router.one/models.
Is there a minimum top-up for bulk buying?
The checkout page is the source of truth for the minimum amount. Card and Alipay top-ups currently usually start at $5 USD equivalent; RMB amounts are converted and shown at checkout using the current FX rate. Stablecoin top-ups usually start at $5 USD equivalent.
How do I resell volume to my own customers?
Build your service on Router One as the upstream: issue one key per customer or tier, used server-side in your service and capped on wallet charges, meter with the per-request usage data, and set your customer pricing in your own portal. Reconcile your upstream cost from settled request charges, including applicable discounts and plan multipliers; checkout-visible FX/channel fees remain separate. Your customer pricing and margin are your own.
Can I pay for large top-ups without a US credit card?
Yes. Top up with a card or Alipay through one hosted checkout, or with USDT/USDC on six chains (Tron, BSC, Ethereum, Polygon, Base, Arbitrum). No US credit card required.
Will volume pricing be negotiable later?
This page does not announce a future volume-pricing program. Plan with the current published terms, catalog rates and your settled request charges; applicable account/model discounts or plan multipliers do not establish a general wholesale tier.
Related
- LLM API reseller
- Pricing methodology
- API relay station
- White-label LLM API
- LLM observability
- Pay with crypto
- Referral program (5% commission on top-ups)
Start with a wallet and per-key budgets
Get your API key