| 1 | command: /tokens |
| 2 | is_error: false |
| 3 | message: |
| 4 | Token Usage: |
| 5 | ───────────────────────────── |
| 6 | Active context: ~48 / 1000000 (0.0%) |
| 7 | Last API input: 100 (turn telemetry; may count repeated prefix across tool rounds) |
| 8 | Last API output: 25 |
| 9 | Cache hit/miss: 70 hit / 30 miss (telemetry/cost only) |
| 10 | Cumulative tokens: 1234 (session usage telemetry) |
| 11 | Priced amount: $0.0500 |
| 12 | API messages: 0 |
| 13 | Chat messages: 0 |
| 14 | Model: deepseek-v4-pro |
| 15 | Cache-write (cache-creation) tokens this session: not reported. Billed above the input rate where the provider publishes a write premium; see /cache for the per-turn breakdown. |
| 16 | |
| 17 | This is an estimate, not a bill: it is computed locally from provider-reported token usage and published rates, and can differ from your invoice. |
| 18 | Covered: 1 of 1 money-metered turn(s) priced. |
| 19 | action: <none> |
| 20 |