Stats
What each market cleared at, and the tokens processed behind it.
Every market · preview
Clearing level
Dollars per 1M input tokens (90% cached, 2% output)
$0.0000
Level history is still loading. Each market is fetched in turn.
- market-preview$0.0403
Usage
Tokens per bucket, cheapest band first
No token volume in this range yet
By model
Model details| Model | Level | Input | Cache hits | Output | Requests | Share |
|---|---|---|---|---|---|---|
| market-previewpreview | $0.0403 | 0 | 0.0% of input, 0 tokens | 0 | 0 | 0.0% |
| kimi-k3 | Fixed price | 0 | 0.0% of input, 0 tokens | 0 | 0 | 0.0% |
| glm-5.3 | Fixed price | 0 | 0.0% of input, 0 tokens | 0 | 0 | 0.0% |
| glm-5.3-flash | Fixed price | 0 | 0.0% of input, 0 tokens | 0 | 0 | 0.0% |
| deepseek-v4.1-flash | Fixed price | 0 | 0.0% of input, 0 tokens | 0 | 0 | 0.0% |
No billed traffic in this range yet.
How these figures are counted
Aggregated across all accounts and grouped only by model and time bucket, so no individual account's activity is exposed.
Internal uptime-probe traffic is excluded. Cache hits are a subset of input, so the two input bands add up to it and the cache column is a share of it.
Every clearing level on this page is live. The token and request totals are counted over the window and refresh every few seconds.