Enterprise

The things we run for you. Covered public-catalog spend in, eval-gated changes out, and a causal-cache verified ledger that starts at the honest zero.

Pricing

The full stacklive demos · illustrative numbers

Caveman Cloud · the managed planein private development · waitlist open

Compression, every method

Watch it work. Nine compressors for the traffic agents actually send — JSON, logs, code, tables, bulk context — and you can always get the original back.

est. tokens the model sees

1,842 → 1,842−74%

{"files": [
  {"name": "proxy.go", "size": 48213, "sha": "9c1f2ea7",
    "mode": "0644", "uid": 501, "gid": 20, "mtime": "2026-07-22T09:14:02Z",
    "atime": "2026-07-22T11:02:41Z", "ctime": "2026-07-22T09:14:02Z" },
  {"name": "plan.go", "size": 9911, "sha": "e07ab112", "mode": "0644", … },
  {"name": "cache.go", "size": 18402, "sha": "77b09e0c", "mode": "0644", … },
  … 45 more objects, identical shape …
  · 47 rows kept as {name, size, sha}
]}
‹caveman: shrank · 1,842→486 est. tok · repeated shape elided · recover: ccr_9f2c…›

+ schemas · diffs · search · html

illustrative samples · est. tokens (o200k) · not production engine output · originals recoverable via ccr

Every dollar explains itself

Who spent it, through which key, on which model — and why it burned.

uncached prefixoversized toolspremium on easy workretriesrest

$341.70

Cave Plan

Ranked moves with a dollar figure on each, read from your own traffic.

Cache the repeated system prefixzero app change

$0/day

Defer 14 unused tool schemasSDK

$0/day

Route eval-runs to a cheaper modeleval-gated

$0/day

found today, on your traffic$0/day · inferred

Model routing

The cheapest model in your pool that passes your evals — or it stays put.

summarize tool output

sonnet-5 → haiku-4-5 · gate ✓

write the migration

stays — nothing cheaper passed

extract invoice fields

gpt-5.5 → gemini-3-flash · gate ✓

Eval-gated rollout

Nothing touches live traffic until it passes its quality gate.

recordreplayshadowcanaryactive

gate ✓ at every stage → active

Caching, done for you

Provider-native cache hints, added upstream only.

req 1 · prefix 41k → sent + cache_control

req 2 · same prefix → cache hit

req 3 · same prefix → cache hit

model-visible bytes untouched · today's only verified dollars

Runs where your prompts live

One engine, three rooms — on Enterprise our cloud sees nothing at all.

hosted

Managed gateway, BYOK — never resold.

your cloud

Helm-deployed in your VPC.

on-prem

Your datacenter · ZDR — the uplink refuses.

sso/saml · five-role rbac · row-level org isolation · audit log · ed25519-signed receipts (manual export today)

spend is priced from provider usage × the public catalog — unknown models stay unpriced · verified savings start at $0 and move only on provider-causal evidence

The dashboard0 beats · demo data

acme-prod · requestsdemo data

Truthful catalog subtotals

Complete provider-reported usage is priced from the public catalog. Incomplete usage and unknown models remain visibly unpriced, never guessed.

Estimates go in.
Receipts come out.

Every saving runs one loop before it counts: measured at the gateway, planned in dollars, fixed by a Cave Agent PR you review, verified on your live traffic. Nothing is claimed on a projection.

Then the verified result feeds the next plan, and the loop keeps running.

Measure catalog-priced usage

Byte-safe gatewayProvider countersCatalog coverage

Plan in dollars

Cave ScoreRanked movesInferred, per day

Fix by agent PR

Cave AgentScoped PRsYou review & merge

Verify on live traffic

Eval gatesShadow & canaryCausal cache onlyAuto-signing off

↺ verified feeds the next plan

Planned gainshare applies only to qualifying verified savings; automatic charging is disabled today. Flat plans on pricing.

Truthful catalog subtotals

Estimates go in.Receipts come out.

Measure catalog-priced usage

Plan in dollars

Fix by agent PR

Verify on live traffic

Estimates go in.
Receipts come out.