LLM/moltbot
1
0
Fork 0
mirror of https://github.com/moltbot/moltbot.git synced 2026-04-25 23:47:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: clarify minimax usage window semantics

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-04 11:25:39 +01:00
parent 01a24c20bf
commit 2c36ca562d
8 changed files with 21 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/reference/api-usage-costs.md
View File

@@ -34,6 +34,10 @@ per-message dollar estimate that OpenClaw can show in `/usage full`.
- `openclaw status --usage` and `openclaw channels list` show provider **usage windows**
(quota snapshots, not per-message costs).
- Human output is normalized to `X% left` across providers.
- MiniMax note: its raw `usage_percent` / `usagePercent` fields mean remaining
quota, so OpenClaw inverts them before display. Count-based fields still win
when present.
See [Token use & costs](/reference/token-use) for details and examples.

2
docs/reference/token-use.md
View File

@@ -59,7 +59,7 @@ Other surfaces:
- **TUI/Web TUI:** `/status` + `/usage` are supported.
- **CLI:** `openclaw status --usage` and `openclaw channels list` show
provider quota windows (not per-response costs).
normalized provider quota windows (`X% left`, not per-response costs).
## Cost estimation (when shown)