Understanding token prices
Input, output, cache, and input-equivalent allowances.
Read prices in the same unit
Public model comparisons use $ / 1M tokens. The detail view preserves exact original source values and shows a per-million comparison only for known token-priced fields. For a non-text or other source field without an explicit unit, it shows the value and marks the unit unspecified instead of inventing a conversion. Conditional overrides show their thresholds and dates alongside the prices that apply under those conditions.
Input and output have separate prices. Cache reads, cache writes, batch processing, long-context tiers, and non-text operations may have their own conditions or units. Your accepted rate card controls your agreement.
What 1 BT means
1 BT means 1,000,000,000 input-equivalent tokens. This is the minimum for a new agreement. A firm offer is an instant clip at the provider’s published quantity, which cannot be below this minimum. An RFQ is used when the terms need negotiation.
Input-equivalent allowance describes consumption relative to the agreement’s input base rate. It is not a promise of the same number of output tokens or requests. A more expensive usage class consumes more equivalent allowance.
A worked example
The following rates are illustrative, not a live offer:
| Usage class | Agreed price ($ / 1M tokens) | Equivalent multiplier |
|---|---|---|
| Uncached input | $1.00 / 1M tokens | 1× |
| Output | $4.00 / 1M tokens | 4× |
| Cache read | $0.10 / 1M tokens | 0.1× |
| Cache write | $1.25 / 1M tokens | 1.25× |
At these example rates, a 1 BT agreement represents $1,000 of input-equivalent consumption: one billion tokens at $1 / 1M tokens. Suppose a request group uses one million uncached input tokens, 250,000 output tokens, and 500,000 cache-read tokens:
| Usage | Charge |
|---|---|
| 1,000,000 input tokens | $1.00 |
| 250,000 output tokens | $1.00 |
| 500,000 cache-read tokens | $0.05 |
| Total | $2.05 — 2.05 million input-equivalent tokens (0.00205 BT) |
The service uses the exact agreed prices and actual token quantities for accounting. Rounded on-screen multipliers help you understand the result; they do not control settlement.
Cache and batch conditions
A published cache price does not guarantee a cache hit. Cache reads and writes are separate usage classes, and a provider may have different retention-duration or tier rules. Cached input must not also be charged as ordinary uncached input.
Batch is a distinct execution mode that needs a supported adapter and an agreed delivery deadline. It is not a universal discount. Do not combine batch and cache reductions unless the provider’s accepted schedule explicitly supports that combination.
Zero prices and other units
Some public models have a zero input reference price. A zero price cannot define a division-based input-equivalent multiplier. A standard wholesale allowance needs a separately defined positive input rate card before it can be traded.
Images, audio duration, video duration, search calls, and per-request fees are not ordinary text tokens. They need explicit units, supported capabilities, and applicable quoted terms. An unsupported billable operation is rejected rather than assigned an invented token charge.
Prices in a multi-provider agreement
An RFQ can be fulfilled through multiple accepted provider allocations. Each allocation keeps its own rate card, allowance, remaining value, and delivery terms. Use Provider allocation rate cards in the agreement to inspect these prices; the agreement overview does not replace the individual cards.
For an illustrative request for 10 BT (10 billion input-equivalent tokens), a 6 BT allocation at $1 / 1M tokens of input represents $6,000, while a 4 BT allocation at $2 / 1M tokens of input represents $8,000. The combined agreed value is $14,000. These are example rates, not a live offer.
Output and cache consumption use the rate card of the allocation that actually serves the request. Do not apply one provider’s output multiplier or cache price to every provider in the agreement.
Before accepting
Check input and output prices, cache conditions, supported execution modes, tier thresholds, currency, expiry, and delivery terms. Ask for clarification through your RFQ before accepting a rate card you do not understand.