DocumentationAPI v1
Stateless stack decision check
Evaluate an inline workload, candidate model list and evaluation measurements against live Witness prices and provider compliance terms in memory, with no API key and zero retention.
POST /api/v1/decidecurl -X POST https://vitna.ai/api/v1/decide \
-H "content-type: application/json" \
-d '{
"workload": {
"id": "ci/support-triage",
"classId": "model",
"incumbentSkuId": "openai/gpt-5.6-luna",
"unitLabel": "tickets",
"unitProfile": { "inputTokensPerUnit": 2000, "outputTokensPerUnit": 500 },
"monthlyVolume": 100000,
"constraints": {
"qualityFloor": 94.0,
"economicThresholdPct": 15,
"edgeCaseVeto": ["pii-leak"],
"requiresZeroRetention": true
},
"priority": "economics"
},
"candidates": ["anthropic/claude-sonnet-4-6"],
"evidence": [
{ "skuId": "openai/gpt-5.6-luna", "measuredAt": "2026-09-14", "metrics": { "successRatePct": 96.0 } },
{ "skuId": "anthropic/claude-sonnet-4-6", "measuredAt": "2026-09-14", "metrics": { "successRatePct": 95.5 } }
]
}'How candidates are weighed
Every candidate runs through the same pure decide() engine used by aperture:decide:
- Eligibility against
witness.provider_term(requiresZeroRetention,requiresNoTraining,requiresRegionsandallowsProviders), three-provenance capability and runtime speed bounds (requiresCapabilitiesandminContextTokensoverdeclared_mirror,minThroughputToksSecandmaxTtftMsovermeasured_third_party, andrequiresVerifiedCapabilitiesover customerverifiedCapabilitiesevidence carryingnandsourceRef), citing the exact term IDs, mirror readings, and customer evidence rows inspected. - Quality floor (
candidate.successRatePct >= constraints.qualityFloor). - Critical edge-case vetoes (intersection of reported
edgeCaseFailureswithconstraints.edgeCaseVeto, downgrading otherwise economic candidates totest). - Cost per successful unit over the Witness market tape (
savingsRatePct >= economicThresholdPct).
Inline workload profiles, candidate lists and measurements are evaluated purely in memory (Cache-Control: no-store) and never written to disk or the database.
Response shape
{
"workload": {
"id": "ci/support-triage",
"name": "Stateless CI check",
"classId": "model",
"incumbentSkuId": "openai/gpt-5.6-luna",
"incumbentName": "GPT-5.6 Luna",
"unitLabel": "tickets",
"monthlyVolume": 100000,
"priority": "economics",
"activeRequirements": ["requiresZeroRetention"]
},
"recommended": {
"action": "switch",
"skuId": "anthropic/claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"savingsRatePct": 24.5,
"annualSavingsUsd": 3420,
"reason": "The candidate clears the quality floor with no critical failures and improves cost per successful task by 24.5%."
},
"evaluations": [
{
"skuId": "anthropic/claude-sonnet-4-6",
"name": "Claude Sonnet 4.6",
"evaluable": true,
"outcome": "switch",
"reason": "The candidate clears the quality floor with no critical failures and improves cost per successful task by 24.5%.",
"figures": {},
"thresholds": {},
"checks": [],
"inputs": {
"pricePeriodIds": [101, 102],
"enteredPriceIds": [],
"evidenceIds": [],
"evidenceSources": [],
"termIds": [8]
}
}
],
"privacy": "Evaluated in memory with zero retention; inline workload profiles, candidates, and evaluation figures are never stored.",
"meta": {
"generatedAt": "2026-09-14T18:35:00.000Z",
"source": "database",
"count": 1
}
}