Models
Every market here has its own clearing level and order book. Fixed-price models are in their own table below, each at three published prices per 1M tokens.
How uptime is measured
Every 5 minutes, a real chat completion runs end to end against each model, through the same public API a customer uses.
The uptime, failure and latency figures on this page are those checks.
Clearing level · every market · preview
Markets
One row per market, sortable by any heading. Levels move with the market; the window figures refresh every 15 seconds.
| Details | |||||
|---|---|---|---|---|---|
| market-previewdefaultpreview | $0.0426 | Pending | 0 |
Fixed price
One row per fixed-price model, with its prices per 1M tokens of each kind. The token figures refresh every 15 seconds.
| Model | Cache-hit | Cache-miss | Output | Context | Max output | Tokens | Details |
|---|---|---|---|---|---|---|---|
| kimi-k3 | $0.1000 | $1.0000 | $5.0000 | 1,048,576 | 128,000 | 0 | |
| glm-5.3 | $0.0750 | $0.7500 | $2.2500 | 1,048,576 | 128,000 | 0 | |
| glm-5.3-flash | $0.0200 | $0.1000 | $0.3000 | 1,048,576 | 128,000 | 0 | |
| deepseek-v4.1-flash | $0.0100 | $0.1000 | $0.4000 | 1,048,576 | 128,000 | 0 |
Uptime, all models
Every model's probes pooled. For one model, open its row above.
Uptime
Pending
Checks
0
Failures
0
Latency
Pending
Queue wait
Pending
Checks begin once capacity is serving a model.