Market
Every market is its own book. You bid a ceiling, and pay the clearing level at the moment your request executes.
A preview of the market that opens once there is traction and compute behind it. Its prices are simulated until then; fixed-price models run today.
Clearing level · market-preview · preview
Per 1M tokens: $0.0188 cache-hit · $0.1881 cache-miss · $0.3762 output
A price_lock request pays at most the locked price, and cancels with no charge if it has not started within 10 seconds.
The basis is the margin over the level, and a ceiling rather than a charge. See how the lock works.
- Your bid is a ceiling. You pay the clearing level at execution, up to that.
- A request waits in the book until the level reaches its bid. It is never rejected on price, and you can cancel it while it waits.
- Token weights are 1:10:20, cache-hit input to cache-miss input to output. Full details in the docs
Levels
Loading level history…
Last 24 hours
- High
- $0.0668
- Low
- $0.0340
- Mean
- $0.0437
Price calculator
Empty follows the live level. Type a level to price this workload at a busier moment.
| Component | At current level |
|---|---|
| Cache-hit input | $0.0169 |
| Cache-miss input | $0.0188 |
| Output | $0.007525 |
| Total | $0.0433 |
The level is the price of 1M input tokens at the reference mix. At the current level that works out to $0.0188 / $0.1881 / $0.3762 per 1M hit / miss / output tokens.
How the level is normalized
The reference mix is 90% cache-hit, 10% cache-miss, and output at 2% of input.
Weights are ×1 hit, ×10 miss and ×20 output, divided by 2.3, so the reference mix preset above totals exactly the level.