SAKANAL Console
24h7d30d
$0.8479
Actual spend (24h)
537 calls · 24h window
$0.8460
Counterfactual — burn without SAKANAL
priced for 93.48% of calls — a floor, not a total
$0.0000
Dividend (counterfactual − actual)
= cache + routing + compaction savings
Read the counterfactual honestly. The "burn without SAKANAL" figure is only populated for the 93.48% of calls the gateway could price. The rest have no baseline (routing is shadow-first and the default-model table does not exist), so the true number is higher — and the console will not guess it. On a fleet this small, the Value view is a correctness proof, not a savings case.

Savings by lever

LeverFormulaSaved (USD)Status
Routing Savingscounterfactual(model requested) − actual cost$0.0000PLACEHOLDER
route_applied = 0 in window — routing is shadow-first and has not re-routed a live request yet.
Caching Savingscache_read_tokens / 1e6 × (input_rate − cached_input_rate)$0.0000LIVE_PARTIAL
31,060 cache-read token(s) in window. Made-visible, never caused.
Compaction — Dropped × RateDropped_Tokens × Model_Rate = jev_compact_saved / 1e6 × input_rate$0.0000PLACEHOLDER
0 dropped token(s) in window — shadow-only, and the target model has no seeded rate, so this reads 0 by the 022 rule.

Master equation (migration 022): Dividend = Σ(counterfactual − cost) = Σ(savings_cache) + Σ(savings_routing) + Σ(savings_compaction)

Go-live gate (migration 022) — 2/4

The green savings number stays off until all four conditions pass.

#ConditionVerdictDetail
G1Every spending model has a verified rate rowFAILmissing: google/gemini-3.1-flash-lite, typesafe/jev-latest, deepseek/deepseek-v4-flash-0731, qwen/qwen3.8-max
G2Gemini cache_read_tokens non-zeroPASS12,252 tokens
G3default_model_per_feature covers spending featuresFAILtable absent — routing baseline not computable
G4Every rate row has a non-empty sourcePASSall sources set

Rate coverage — spending models vs model_rates

ModelSpend (24h)Rate row
google/gemini-3.1-flash-lite$0.5724missing
google/gemini-2.5-flash$0.1979seeded
deepseek/deepseek-v4-flash$0.0498seeded
google/gemini-2.5-flash-lite$0.0241seeded
typesafe/jev-latest$0.0019missing
deepseek/deepseek-v4-flash-0731$0.0014missing
deepseek/deepseek-chat$0.0005seeded
qwen/qwen3.8-max$0.0000missing
openai/gpt-4o-mini$0.0000seeded

Missing rates: google/gemini-3.1-flash-lite, typesafe/jev-latest, deepseek/deepseek-v4-flash-0731, qwen/qwen3.8-max — these models write 0 savings (022 rule: never guess).

Generated 2026-09-28 13:44:04Z · window 24h