dsh-meow-cachebilling
Per-round cache billing inside the composer context-meter popover: what the current call spends on cache hits, misses, and output in CNY, with automatic official peak/off-peak and per-model pricing; hidden on non-official DeepSeek routes.
点开输入框旁的上下文圆环即见本轮账单：缓存命中/未命中/输出各花多少钱（¥），官方峰谷价与模型分价自动判定；非 DeepSeek 官方路由不显示。
How to install
dsh plugin add meow-cachebilling About
meow-cachebilling English 难道只有我在关心怎么省钱？你们都那么有钱的吗…… 为什么会有这个插件 dsh缓存命中率高，ds服务器缓存处理也得当，价格也便宜，导致可能很多人都忽略了—— 单价再便宜，当上下文越来越长的时候，它还是会越来越贵。 到最后一算，你实际上付的钱，可能90%以上都是为了买缓存。 也就是说如果有更好的换窗口策略，及时换窗口，ds的费用能大幅度下降。 这是真的，我试了换窗口勤快的策略，试了两天，然后发现，真的便宜了。 我让GPT给我算的，算法是这样的： 缓存命中实际上都是聊过的上下文，每轮带着，所以显得多。 但未命中的输入和ai输出，才是硬梆梆不能少的实际使用，是不是？ 所以或许应该用“实际使用”去衡量两天不同的工作量，并比较两天的性价比。 GPT算出来我勤换窗口时，便宜了50.1%。 所以，正确的deepseek使用姿势是： 不断开新窗口，旧窗口就再也不动了。 很长的旧窗口，每动用一次，都要为缓存付很多钱。 如果是时间久了、服务器那边缓存都删除了的旧窗口，那想必更是天价，全都按miss算啊。 所以旧窗口碰都不碰是最优解。 （所以还需要配合记忆插件来把旧窗口的有用信息带走） 但是，具体什么时候换窗口，你就需要衡量了。 换窗口的成本是： AI需要重读代码的miss输入（可以通过fork减少这项成本）。 你需要重新介绍任务和规则的人力成本（可以通…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 28
- mo. downloads
- –
- Last push
- 2026-09-24
- Created
- 2026-08-22
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin, curated:0xsline/awesome-deepseek-harness
- Topics
- billing, cache, cost-tracker, deepseek, deepseek-harness, dsh, dsh-plugin
Related plugins
TokenLedger
zh667/TokenLedger
Sidebar usage panel that attributes tokens to the relay site that served each request, read from your existing provider config: today/month/all-time totals, per-site and per-model breakdowns, a year activity heatmap, and New API / Sub2API / DeepSeek balances.
dsh-context
bowenliang123/dsh-context
DSH context insight panel: Context dashboard + /context command + Context browser — one-stop context lifecycle management with categorized composition, content details, evolution trends, compaction/injection events, and stats.
dsh-usage-statistics-panel
HaoyueQin/dsh-usage-statistics-panel
Usage statistics settings panel: 26-week activity heatmap, daily token trend with a cache hit-rate curve, per-model donut and breakdown, time-range filters, summary cards, one-time historical backfill and lossless rebuild.
dsh-all-usage
ParticleLight/dsh-all-usage
Analyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.