Pricing

UberLLM's pricing is deliberately simple and transparent.

How pricing works

Every request is routed to the cheapest healthy seller for that model. The price you see on uberllm.dev and at GET https://api.uberllm.dev/api/v1/public/models is the seller's price plus UberLLM's 10% fee, already included — the price shown is the price you pay. The % off list stays the same, because list and live prices both include the fee.

You are billed for what each request actually used, at that price. You see the cost of every call in Dashboard → Activity. If a call ever comes back without a reported cost, UberLLM bills it from the model's shown price and token usage instead. A single call can come in under the shown price when a cheaper seller serves it. A request that fails costs nothing.

Prepaid credits + 5% credit fee

Inference is prepaid. New accounts start at $0 — add credits before your first call. When you top up, a 5% fee applies to the credit purchase — the fee is on the money-in, separate from the 10% fee in the price of each request. Example:

(Credited = amount ÷ 1.05.) Top-ups are between $5 and $10,000, paid via Stripe on Dashboard → Credits; your balance is drawn down per request at the price each call actually cost.

Spend controls

• Per-key spend limits — set a daily / monthly / lifetime cap when you create a key. Requests that would exceed it return 402 key_spend_cap_exceeded.
• Per-key rate limits — an optional requests-per-minute ceiling per key.
• Balance floor — when credits run out, requests return 402 insufficient_credits until you top up. Reservations for in-flight requests are released if the request aborts or fails.

See Errors for the exact 402 shapes.