# AI use cases for DSH Cost Meter (Han-1413141/dsh-cost-meter)

Repo: [Han-1413141/dsh-cost-meter](https://github.com/Han-1413141/dsh-cost-meter) | Use cases: 5 | Page: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/

dsh-cost-meter is a cost tracking plugin for the DeepSeek Harness web GUI that shows session and model costs, token usage, budgets, provider balances, and coding-plan quotas.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Track what each DSH conversation costs per day: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/track-conversation-and-daily-spend/
- Watch coding plan and OpenCode Go quota before you hit a limit: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/watch-coding-plan-and-go-quota-limits/
- Set a spending budget and get warned before you go over: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/set-budget-and-get-overspend-warnings/
- Compare model token prices before picking a model: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/compare-model-prices-before-choosing/
- Plan heavy model work around peak and off-peak pricing hours: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/schedule-heavy-work-around-peak-hours/

## How to track what each DSH conversation costs per day with DSH Cost Meter

Repo: [Han-1413141/dsh-cost-meter](https://github.com/Han-1413141/dsh-cost-meter) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

See live cost and token totals per conversation, plus daily and period statistics inside DSH.

**Who it is for:** A developer using DSH daily who wants to know which conversations and models drive their spend.

**The problem:** Model usage costs are hard to attribute to a single conversation or day when you work across many sessions.

**The outcome:** You can read the accumulated cost for the current conversation, today's total, and day, week, or month statistics with per-model and per-conversation rankings.

### Steps

1. Install the plugin with `npm install dsh-cost-meter`, then follow the Installation section of the README. (inferred, check the README)
2. Fully restart DSH after the install.
3. Open a conversation and read the live cost and input, cache, and output token counts below the composer.
4. Open Settings → Cost → Cost statistics and select Day, Week, or Month to review totals and rankings.

### Prompt to paste into your agent

```text
Using the dsh-cost-meter plugin in DeepSeek Harness 0.2.0 or later, open Settings → Cost → Cost statistics and report the total cost and call count for <period>, ranked by model. Verify that today's total matches the Summary cards on the Settings page.
```

### Caveat

Cost figures come from the plugin's own metering and the README does not say how they reconcile with a provider invoice.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/track-conversation-and-daily-spend/

## How to watch coding plan and OpenCode Go quota before you hit a limit with DSH Cost Meter

Repo: [Han-1413141/dsh-cost-meter](https://github.com/Han-1413141/dsh-cost-meter) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README

Show rolling usage percentages and reset times for supported coding plans and OpenCode Go in the sidebar and quota strip.

**Who it is for:** A developer on a coding subscription plan who runs long coding sessions and needs to pace usage before a window resets.

**The problem:** Subscription windows such as 5-hour or weekly limits run out without warning, which stops work in the middle of a task.

**The outcome:** You see used percentage and reset times for each enabled window, and a chip row above the input box flags usage at 80 percent or more.

### Steps

1. Open Settings → Cost and find the Coding plan quotas section.
2. Turn on the enable switch for each vendor you use and enter its key, or leave it blank to use the auto-discovery options the README lists for OpenCode Go.
3. Set the display position and refresh interval for each enabled vendor.
4. Turn on the quota strip in Display settings so the window percentages show above the input box.
5. Click a chip in the quota strip to refresh that vendor's data immediately.

### Prompt to paste into your agent

```text
Using the dsh-cost-meter plugin in DeepSeek Harness 0.2.0 or later, read the current usage percentage and reset time for each enabled coding plan window and for OpenCode Go, then list any window at 80 percent or more. Verify that the values match the sidebar quota cards for the same vendors.
```

### Caveat

The README says that without a valid snapshot, SCNet monthly usage is estimated from the local ledger, so those figures are estimates rather than live vendor readings.

Risk, credentials: Quota queries need vendor keys, and Xiaomi MiMo uses a console cookie, so store those credentials only in the plugin settings and never paste them into a shared agent prompt.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/watch-coding-plan-and-go-quota-limits/

## How to set a spending budget and get warned before you go over with DSH Cost Meter

Repo: [Han-1413141/dsh-cost-meter](https://github.com/Han-1413141/dsh-cost-meter) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Track budget used percentage and today's share of budget, with warnings at 80 percent and over-budget at 100 percent.

**Who it is for:** A developer or team lead who has a fixed monthly or daily amount for model usage and needs an early warning.

**The problem:** Spending drifts past a set amount when no one checks running totals against the limit.

**The outcome:** The budget box in the sidebar shows used percentage, a progress bar, and how much of the limit is used, and the quota strip shows the budget chip.

### Steps

1. Open Settings → Cost and enter your budget amount.
2. Check the budget box between the balance row and the settings button in the sidebar.
3. Watch for the warning state at 80 percent and the over-budget state at 100 percent.
4. Turn on the quota strip to see budget used percentage above the input box.

### Prompt to paste into your agent

```text
Using the dsh-cost-meter plugin in DeepSeek Harness 0.2.0 or later, read the current budget used percentage and today's cost against the budget limit, and say whether the warning or over-budget state applies. Verify that the figure matches the budget box in the sidebar.
```

### Caveat

The README describes the budget as a user-set limit and does not say whether it can cap spending automatically, so it only reports usage.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/set-budget-and-get-overspend-warnings/

## How to compare model token prices before picking a model with DSH Cost Meter

Repo: [Han-1413141/dsh-cost-meter](https://github.com/Han-1413141/dsh-cost-meter) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

Check per-token rates and update times for OpenRouter and multi-vendor models, and sync official prices.

**Who it is for:** A developer choosing between several models who wants current token rates before starting a task.

**The problem:** Rates differ across vendors and change over time, and checking each provider's pricing page is slow.

**The outcome:** You can hover a model in the picker to see its token rates and update time, or search the full catalog in Settings → Cost → Prices.

### Steps

1. Open the model picker in DSH and hover a model to see its token rates and update time.
2. Open Settings → Cost → Prices to search the full catalog.
3. Look for price-change markers in the table and follow the official model links for details.
4. Use the one-click price sync from the official docs when you want the latest table.

### Prompt to paste into your agent

```text
Using the dsh-cost-meter plugin in DeepSeek Harness 0.2.0 or later, search the price catalog in Settings → Cost → Prices for <model name> and report its input and output token rates and last update time. Verify the rates against the official model link shown in the table.
```

### Caveat

The README says the OpenRouter price view needs no API key, but the built-in catalog can lag the official docs until you run a sync.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/compare-model-prices-before-choosing/

## How to plan heavy model work around peak and off-peak pricing hours with DSH Cost Meter

Repo: [Han-1413141/dsh-cost-meter](https://github.com/Han-1413141/dsh-cost-meter) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README

See which hours are peak and get a popup or system alert before pricing switches.

**Who it is for:** A developer or operator who can time large batch or long agent runs and wants to start them in cheaper hours.

**The problem:** Pricing changes by time of day, so long runs started at the wrong hour can cost more without the user noticing.

**The outcome:** You know the peak hours and get an alert ahead of each change, so you can start large jobs in off-peak hours.

### Steps

1. Read the peak/off-peak pricing hours display in the plugin: peak hours are UTC 01:00 to 04:00 and 06:00 to 10:00, and weekends and Chinese public holidays are off-peak all day.
2. Open the peak and off-peak alert settings and choose the position, lead time, and alert type.
3. Wait for the pre-switch popup or system notification before a change.
4. Start large or long runs during off-peak hours.

### Prompt to paste into your agent

```text
Using the dsh-cost-meter plugin in DeepSeek Harness 0.2.0 or later, report whether the current UTC time is peak or off-peak and the next switch time. Verify the result against the peak/off-peak hours display in the plugin.
```

### Caveat

The README gives the peak windows as fixed UTC hours, so the schedule may not match a provider's published pricing if that changes.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/han-1413141-dsh-cost-meter/schedule-heavy-work-around-peak-hours/