Averth
ChatGPT pluginTrue cost of every agent run
Averth is a cost-analysis plugin for AI agents: it measures the fully loaded cost of every agent run. Submit a sanitized batch of runs and get the true cost per accepted outcome, the share of spend burned by the most expensive runs, and an offline replay of the cost policies that would have flagged the waste. Analysis is retrospective only. Averth never enforces policies, never touches live systems, and needs no account and no integration; submit sanitized batches only and redact sensitive free text before submitting.
- Featured
- No
not on the featured shelf
Movement
From our daily snapshots over the last 30 days.
Rank by placement
Rank in Data & analytics
3 listing changes logged · latest Oct 30: Description, Version, Categories. See what changed
In its category
How this plugin compares with others in the same category. Positions are counted within the category, not across the whole directory.
Data & analytics517th of 623 by placement
| # | Plugin | Position | 7d |
|---|---|---|---|
| 515 | #8924 | 1,066places down | |
| 516 | #8941 | 1,074places down | |
| 517 | #8944 | — | |
| 518 | #8950 | — | |
| 519 | #8978 | 1,079places down |
Example prompts
- “Analyze this batch of agent runs and tell me what each accepted outcome really cost.”
- “Which of my agent runs are burning the budget? Show me the expensive tail.”
- “If I had capped every run at $1.00, how much historical spend was on runs that would have been stopped?”
Skills
get-started
Analyze the true cost of AI agent runs with Averth. Use when the user shares agent run data, asks what their agents really cost, or wants to replay a cost policy against past runs.
- Categories
- Sign-in
- On Install
- Capabilities
- Analyze agent run costs, Replay cost policies
- Availability
- Available
- Version
- 1.1.0
- Keywords
- agent, cost, economics, observability, finops
- Created
- October 1, 2026
- More info
- Sponsorship
- Promote this plugin