Axtolab AI Spend Monitor

开发者	axtolab
更新时间	2026年6月19日 05:44
PHP版本:	7.4 及以上
WordPress版本:	7.0
版权:	GPLv2 or later
版权网址:	版权信息

下载

1.0.0 1.0.1

详情介绍:

WordPress 7.0 introduced the AI Client and the Connectors screen: you configure an AI provider API key once, and every plugin on your site can use it. What WordPress does not show you is which plugin is spending your money. AI Spend Monitor records every call made through the WordPress AI Client and gives you a clear dashboard under Axtolab → AI Spend Monitor:

Per-plugin AI usage — see exactly which plugins and themes make AI calls, with calls, prompt tokens, and completion tokens for each.
Estimated cost per plugin — token counts are converted to an estimated USD cost using bundled list prices for popular OpenAI, Anthropic, and Google models.
Editable cost rates — a "Cost rates" tab lets you adjust the per-model input/output prices to match your provider plan or a price change. Saving re-estimates previously recorded calls too, so the whole dashboard reflects your rates. No code required.
Daily cost chart — a 30-day view of your estimated AI spend, so a sudden spike is visible the day it happens, not when the invoice arrives.
Recent call log — the latest AI calls with source, provider, model, and token counts.
CSV export — download the recorded calls for any period for accounting or review: source plugin, provider, model, tokens, and estimated cost per call.
Spend notification — optionally get one email per month when estimated sitewide AI spend passes a dollar amount you choose.
Zero configuration — activate it and it starts recording. No API keys, no account, no setup.

How it works The plugin listens to the WordPress AI Client's lifecycle hooks. When any plugin calls the AI Client, the call's token usage and model metadata are recorded in a local database table, and the calling plugin is identified automatically. Old records are pruned after 90 days (filterable). Privacy All data stays on your site. The plugin records token counts and metadata only — it does not store prompt or response content, and it does not send anything to any external service. There are no remote calls, no tracking, and no account requirement. For developers

aismon_usage_recorded — action fired after each recorded call.
aismon_cost_rates — filter the model price table used for estimates.
aismon_retention_days — filter the data retention window (default 90 days).
aismon_dashboard_after_summary — action to render additional dashboard panels.

安装:

Install the plugin from the WordPress.org plugin directory, or upload the plugin zip via Plugins → Add New Plugin → Upload Plugin.
Activate the plugin.
Go to Axtolab → AI Spend Monitor in your WordPress admin to view the dashboard.

The plugin needs WordPress 7.0 or newer to record AI calls — that's the version that introduced the WordPress AI Client. It activates on older versions but will not record anything until you upgrade. No API keys, no account, no setup steps required.

屏幕截图:

升级注意事项:

1.0.1 Adds an editable Cost rates tab so you can match estimates to your provider pricing without code. 1.0.0 Initial release.

常见问题:

Does this work without WordPress 7.0?

The plugin activates on older versions but can only record usage on WordPress 7.0 or newer, because it relies on the AI Client that ships with 7.0.

Are the cost figures exact?

No — they are estimates. Costs are calculated from recorded token counts using published list prices per model (standard tier). Caching and batch discounts are not modeled, and providers change prices. Always treat your provider's invoice as the source of truth. You can adjust any per-model price on the Cost rates tab (no code required); saving also re-estimates previously recorded calls. Developers can layer further changes on the aismon_cost_rates filter.

Does it record my prompts?

No. Only token counts, provider, model, capability, and the calling plugin are stored. Prompt and response content is never recorded.

Does it slow down AI calls?

No. Recording happens after the AI call completes and is a single local database insert. If recording ever fails, the original AI call is unaffected.

Can it alert me about spend?

Yes — set a monthly dollar amount on the dashboard and the plugin emails you once per month when estimated sitewide spend passes it. This is a notification only.

Can it block or limit AI usage?

This plugin is a monitor: it shows you usage and cost, and can notify you. It does not block calls or enforce budgets.

更新日志:

1.0.1

New "Cost rates" tab: edit per-model input/output prices from the dashboard, no code required.
Saving rates re-estimates previously recorded calls, so existing dashboard totals reflect your prices.
Overrides are stored as deltas from the bundled defaults, so untouched models keep tracking future default-price updates.

1.0.0

Initial release: per-plugin AI usage recording, cost estimates, daily cost chart, recent call log, CSV export, monthly spend notification, 90-day retention with daily pruning.