Governance Ledger
Every model call my own AI infrastructure makes is logged, costed, budget-capped, and attributed — automatically, as a byproduct of how it routes work. This is a real excerpt from that ledger.
Last updated: Sep 9, 2026 — real operational data, refreshed periodically, not a live-refreshing feed.
Excerpt subtotal
$0.356603
16 calls, Sep 8-9 2026 — not the same figure as the live window spend below
Calls logged
16
unsampled — every call, not a spot check
Backends in rotation
3
local free-tier → Google → OpenRouter, by policy
Paid vs. free-tier
15 / 16
call volume has grown past what the free tier absorbs — spend is still nowhere near the $30 cap
Per-call ledger
What was requested, what actually served it, what it cost, and which governance function it evidences. Nothing here was written for this page.
| Timestamp | Requested → served | Tokens in/out | Cost | Pool | Quality | Evidences |
|---|---|---|---|---|---|---|
| Sep 08 05:43:55 | gpt-terra→openai/gpt-5.6-terra | 1253 / 3800 | $0.048106 | OpenRouter | — | MAPMANAGE |
| Sep 08 06:02:32 | glm-5.2→z-ai/glm-5.2 | 1483 / 7431 | $0.022873 | OpenRouter | — | MAPMANAGE |
| Sep 08 06:17:52 | glm-5.2→z-ai/glm-5.2 | 5017 / 8192 | $0.029717 | OpenRouter | — | MAPMANAGE |
| Sep 08 14:04:03 | glm-5.2→z-ai/glm-5.2 | 6131 / 3309 | $0.015969 | OpenRouter | — | MAPMANAGE |
| Sep 08 14:05:58 | glm-5.2→z-ai/glm-5.2 | 7072 / 2376 | $0.014045 | OpenRouter | — | MAPMANAGE |
| Sep 08 14:06:00 | gemini-flash→gemini-3.8-flash | 847 / 36 | $0.000770 | free-tier | — | MAP |
| Sep 08 14:07:35 | glm-5.2→z-ai/glm-5.2 | 15839 / 1635 | $0.020264 | OpenRouter | — | MAPMANAGE |
| Sep 08 14:08:52 | glm-5.2→z-ai/glm-5.2 | 2240 / 2837 | $0.010777 | OpenRouter | — | MAPMANAGE |
| Sep 09 14:04:09 | glm-5.2→z-ai/glm-5.2 | 10138 / 3642 | $0.020850 | OpenRouter | — | MAPMANAGE |
| Sep 09 14:06:22 | glm-5.2→z-ai/glm-5.2 | 2461 / 2197 | $0.009047 | OpenRouter | — | MAPMANAGE |
| Sep 09 14:08:52 | glm-5.2→z-ai/glm-5.2 | 9852 / 3686 | $0.020708 | OpenRouter | — | MAPMANAGE |
| Sep 09 14:10:50 | glm-5.2→z-ai/glm-5.2 | 4212 / 2302 | $0.011058 | OpenRouter | — | MAPMANAGE |
| Sep 09 14:11:49 | glm-5.2→z-ai/glm-5.2 | 2343 / 1330 | $0.006301 | OpenRouter | — | MAPMANAGE |
| Sep 09 19:09:27 | gpt-terra→openai/gpt-5.6-terra | 1001 / 1837 | $0.024046 | OpenRouter | — | MAPMANAGE |
| Sep 09 19:10:51 | gpt-terra→openai/gpt-5.6-terra | 992 / 4078 | $0.050920 | OpenRouter | — | MAPMANAGE |
| Sep 09 19:22:11 | gpt-terra→openai/gpt-5.6-terra | 1078 / 4083 | $0.051152 | OpenRouter | — | MAPMANAGE |
Gateway snapshot
Checked directly against the gateway's own status tool on Sep 9, 2026 — a separate, fresher check than the ledger rows above, not a live-refreshing counter on this page.
Monthly budget cap
$30.00
hard ceiling, shared across every machine running this infrastructure
Spent this window
$2.98
9.9% of cap — window opened Aug 18, 2026
Per-request ceiling
$1.00
reserved and checked before any single call goes out
Backend health
2 / 3
Google and OpenRouter reachable at last check; local free-tier backend (LM Studio) was down
What this satisfies
Mapped to the NIST AI RMF's four functions — the framework this ledger was built against, not retrofitted to.
GOVERN
A spend policy — $30 per 30-day window, shared across every machine running this infrastructure — set once and enforced automatically on every call.
policy: budget.json
MAP
Every call records what was requested and what actually served it. No AI action happens without a named model and a named route.
field: model → served_model
MEASURE
Token volume and cost are recorded on every call; response quality is scored and attached where evaluated.
field: in / out / cost / quality
MANAGE
Spend against paid credit is checked and reserved before the call goes out — the system can't overspend the cap, because it never sends a request that would.
function: budget reserve-and-charge
Same 16 rows, as an interactive 3D scene
The Gateway Corridor renders this exact ledger as a scene every call passes through — one governed checkpoint, three real backend destinations.
This is the pattern I build into client systems: every AI action logged, budgeted, and attributable — applied to a governed write-path into your ERP, or packaged as evidence for an insurance renewal, instead of a general-purpose AI gateway.
This is spend-level detail. For how findings across the whole automation estate get reviewed and approved, see Automation Oversight →
Want the full picture for your environment?
A discovery call gets you a scoped assessment from the person who builds these engagements — not a form, a conversation.
Book a discovery call