For teams already running an AI gateway

Gateways meter AI traffic. Gesta observes agent behavior.

Your gateway answers one question well: who called which model, and when. The questions that decide budgets, audits, and incident reviews — what did the agent do, what did it produce, what did it actually cost — only exist on the endpoint, where the agent runs.

01 · The bill

Two line items can't price an agent.

Gateway cost reports multiply two numbers: input tokens and output tokens. Agent sessions replay the same context on every turn — so the tokens that dominate the bill are the cache tiers the gateway's arithmetic never sees.

What your gateway seesproxy log
POST /v1/messages 200
model           frontier-large
input_tokens    1,842
output_tokens   697
— — — — — — — — — — — — — —
cost = in × rate + out × rate
     = $0.016
Two tiers priced. Everything else invisible.
What actually happenedsame request
input1,8421%
output6971%
cache write28,41019%
cache read118,20679%
All four tiers at list rates: $0.158 — the gateway's figure was off 10×.

Agent workloads are cache-dominated. Price only input and output, and the bill is wrong in its first digit. Gesta prices every token tier.

Data shown is illustrative

02 · The output

Spend is not output.

A proxy sees traffic — requests, bytes, latency. And model output tokens aren't output either: most of a session is the agent thinking, reading, retrying. Nothing in a request log connects a dollar of spend to work actually produced.

What your gateway seesproxy log
14:02:11  POST /v1/messages  200  2.1 MB  1,204 ms
14:02:19  POST /v1/messages  200  3.4 MB    980 ms
14:02:31  POST /v1/messages  200  1.7 MB    644 ms
14:02:48  POST /v1/messages  200  2.9 MB  1,411 ms
— — — — — — — — — — — — — —
requests 2,417 · bytes out 1.9 GB
Traffic metered. Outcome unknown.
What Gesta seessame session
  • Code authored412 lines
  • Tests authored96 lines
  • Docs authored1,024 words
  • External tools17 MCP calls
  • Session cost$12.40
Every session priced and weighed — at the moment of writing, not after the fact.

A proxy knows what you spent. It can't know what you got. Gesta measures what agents actually author — and a local agent writing files never crosses a proxy at all.

Data shown is illustrative

03 · The audit

A request log is not an audit trail.

When the audit comes, “someone called a model at 09:41” is not an answer. And an agent that talks to a local tool or calls an API directly never traverses your proxy at all — the gateway's log has no row to show.

What your gateway seesproxy log
09:41:07  key prod-07  POST /v1/messages  200

proves: someone, holding this key,
        called a model at 09:41.

cannot answer:
  • is this line of code AI-written?
  • what left in the prompt body?
  • what about calls that never
    routed through the gateway?
Presence proven. Content and provenance unknown.
What Gesta seeson the endpoint
Is this line of code AI-written?
src/auth/token.ts:41–58 → AI-written · session 7f3c · prompt #12 · committed 4f9c2e1
Did customer data leave the network?
prompt #31 attached customers_q2.csv → direct API call, gateway never traversed · flagged at the endpoint
Answered from the session record — not inferred from traffic.

Request logs prove someone called a model. They can't tell you whether a line of code is AI-written, or whether customer data left in a prompt that never touched your gateway. Those answers only exist where the agent runs. That's where Gesta sits.

Data shown is illustrative

Ask your gateway these two questions.

Then ask us.

Run both: your gateway routes traffic; Gesta records behavior.