Get a decision's model cost, per evaluation and in total
Model cost of one decision’s evaluations and previews over a window; reads only. What the decision’s evaluations cost over a window, for the key’s organization and environment. Amounts are US dollars in micros (usd_micros: millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor’s published price, plus an estimate for calls we couldn’t price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as estimated_usd_micros; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in other_spend, outside the per-evaluation numbers, and total adds everything recorded. Per-request cost on evaluate and import_examples is reported cost only. since (inclusive) and until (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).
GET
/
v1
/
decisions
/
{decision_id}
/
usage
Get a decision's model cost, per evaluation and in total
An API key, sent as Authorization: Bearer <key>. Each operation lists the scope its key needs: decisions:evaluate (evaluate and read evaluations), decisions:feedback (your app's feedback) or decisions:develop (everything else, including owner feedback and the review queue). An operation listing no scope takes any scoped key. A key with no scope, or without the operation's, gets 403 INSUFFICIENT_SCOPE.
A name you choose for this decision, such as refund-exception: a lowercase letter, then up to 127 of a-z 0-9 _ . -. Unique in your organization and shared by its test and production keys. The first registration or evaluation under a new one creates the decision.
A name you choose for this decision, such as refund-exception: a lowercase letter, then up to 127 of a-z 0-9 _ . -. Unique in your organization and shared by its test and production keys. The first registration or evaluation under a new one creates the decision.
The environment of the key that made the call: production or test. Evaluations, feedback, reviews and suggestions are separate per environment; decisions and their versions belong to the whole organization.
One group per model.profile and assignment mode, ordered by both. Spend whose evaluation is gone is grouped under the profile unknown, as is dry-run spend, which has no evaluation.
Stored preview runs in the window (mb test, previews, and the one preview each generated suggestion runs), which write no evaluations. Generation's exploratory replays and model call are in other_spend, as is a preview run that stored nothing (uncommitted).
Show child attributes
{"docsConfig":{"theme":"mint","$schema":"https://mintlify.com/docs.json","name":"Moonbounce Decisions API","colors":{"primary":"#1D5AB5","light":"#74A8F0","dark":"#478EF0"},"logo":{"light":"https://mintcdn.com/moonbounce/mWuXGW-nUJSEdABp/logo/lockup-light.svg?fit=max\u0026auto=format\u0026n=mWuXGW-nUJSEdABp\u0026q=85\u0026s=367a5dedb5799a16c5737d136af68dc5","dark":"https://mintcdn.com/moonbounce/mWuXGW-nUJSEdABp/logo/lockup-dark.svg?fit=max\u0026auto=format\u0026n=mWuXGW-nUJSEdABp\u0026q=85\u0026s=3b3e891bc9f1e5b26bee272f878ecd4f","href":"https://moonbounce.ai"},"favicon":{"light":"https://mintcdn.com/moonbounce/XgvwJtU0Z2TC5k2H/logo/symbol-light.svg?fit=max\u0026auto=format\u0026n=XgvwJtU0Z2TC5k2H\u0026q=85\u0026s=cd361cb434cc5cabaa2240471ebc780a","dark":"https://mintcdn.com/moonbounce/XgvwJtU0Z2TC5k2H/logo/symbol-dark.svg?fit=max\u0026auto=format\u0026n=XgvwJtU0Z2TC5k2H\u0026q=85\u0026s=30d3353b4d3a5756ecfadd153e271d89"},"background":{"color":{"light":"#FFFEEE","dark":"#000000"}},"navbar":{"primary":{"type":"button","label":"Request access","href":"https://app.moonbounce.ai"}},"banner":{"content":"Looking for the Clavata policy and labeling API? Those docs are at [docs.clavata.ai](https://docs.clavata.ai). You are on the docs for the Moonbounce decisions platform.","dismissible":true,"type":"info","color":{"light":"#1D5AB5","dark":"#1D5AB5"}},"styling":{"latex":false},"navigation":{"pages":[]}},"deployment":{"deploymentMetadataValue":{"subdomain":"moonbounce","hasAudioNarration":false,"actualSubdomain":"moonbounce","customDomains":["docs.moonbounce.ai"],"gitSource":{"type":"github","owner":"clavataai","repo":"decisions-platform","deployBranch":"main","contentDirectory":"docs/site","isPrivate":true,"mountPath":"","label":"","_id":"6ae8f7a905e268646b31d443"},"entitlements":{},"buildId":"6aee998bf28062a6e44b0f51","clientVersion":"0.0.4076","searchFilterCounts":[{"language":"default","tag":"API reference","count":42},{"language":"default","tag":"Endpoints","count":41},{"language":"default","tag":"Guides","count":15},{"language":"default","tag":"review","count":10},{"language":"default","tag":"decisions","count":6},{"language":"default","tag":"suggestions","count":6},{"language":"default","tag":"feedback","count":5},{"language":"default","tag":"evaluate","count":4},{"language":"default","tag":"objective","count":4},{"language":"default","tag":"Get started","count":3}]},"assistantConfig":{"enableAskAiButton":false,"enableStarterQuestions":false,"enableContextualStarterQuestions":false,"enableAskAiSearchBar":true},"basePath":"","hasChatPermissions":false,"hasWebMcpPermissions":false,"toggles":[{"name":"kill-isr","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-mintlify-slack","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"agent-integrations-settings","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"rbac-expansion","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-pr-grouping","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"custom-prefix","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"analytics-v7","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"user-flows-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"no-publish-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-onboarding","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"llms-txt-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving-live","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"stripTemperatureMiddleware","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"support-platform-pylon-zendesk","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"snapshot-serving","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"instant-rollback","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications-server","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"granular-notifications","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automations-fable","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fixed-ai-action-pricing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"automation-resolve-merge-conflict","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"scoped-publishing","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"mintql","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"page-level-analytics","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-version-history-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"billing-page-v2","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"full-page-search","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workspace-projects","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"assistant-v5","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"fork-pr-previews","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"revalidation-jwt","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-sso-scim","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"hobby-abuse-scan","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"dashboard-inbox","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-signup","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-dual-write","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"workos-enabled","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"approve-review-flow","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"editor-metadata","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"sso-setup-deadline-banner","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"turbopuffer-serve","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"live-agents","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false},{"name":"comment-mode","enabled":true,"variant":{"name":"disabled","enabled":false,"feature_enabled":true},"impressionData":false}],"googleFontsInlined":false},"customCss":[{"filePath":"brand.css","content":":root{--mb-font-sans: \"Helvetica Neue\", Helvetica, Arial, sans-serif;--mb-font-mono: ui-monospace, \"SF Mono\", Menlo, Consolas, monospace;--mb-rule: rgb(225, 230, 240);--mb-rule-strong: rgb(134, 134, 134)}.dark{--mb-rule: rgb(68, 69, 74);--mb-rule-strong: rgb(134, 134, 134)}body{font-family:var(--mb-font-sans)}h1,h2,h3,h4,h5,h6{font-family:var(--mb-font-sans);font-weight:600;letter-spacing:-0.011em}#page-title{letter-spacing:-0.03em;line-height:1.05}code,pre,kbd,samp{font-family:var(--mb-font-mono)}#navbar a[target=\"_blank\"][href=\"https://app.moonbounce.ai\"]>span.absolute{background:rgb(0, 0, 0);border-radius:999px}#navbar a[target=\"_blank\"][href=\"https://app.moonbounce.ai\"] .text-white,#navbar a[target=\"_blank\"][href=\"https://app.moonbounce.ai\"] svg{color:rgb(255, 254, 238)}.dark #navbar a[target=\"_blank\"][href=\"https://app.moonbounce.ai\"]>span.absolute{background:rgb(255, 254, 238)}.dark #navbar a[target=\"_blank\"][href=\"https://app.moonbounce.ai\"] .text-white,.dark #navbar a[target=\"_blank\"][href=\"https://app.moonbounce.ai\"] svg{color:rgb(0, 0, 0)}.card,.callout,.code-block,.accordion,table{border-radius:0;box-shadow:none}.card{border:1px solid var(--mb-rule)}.card:hover{border-color:var(--mb-rule-strong)}"}],"page":{"pagePath":"api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total","slug":"/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total","pageMetadata":{"title":"Get a decision's model cost, per evaluation and in total","description":"Model cost of one decision's evaluations and previews over a window; reads only. What the decision's evaluations cost over a window, for the key's organization and environment. Amounts are US dollars in micros (`usd_micros`: millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor's published price, plus an estimate for calls we couldn't price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as `estimated_usd_micros`; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in `other_spend`, outside the per-evaluation numbers, and `total` adds everything recorded. Per-request `cost` on evaluate and import_examples is reported cost only. `since` (inclusive) and `until` (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/usage","href":"/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total","autogeneratedByOpenApi":true},"description":{"compiledSource":"\"use strict\";\nconst {jsx: _jsx, jsxs: _jsxs} = arguments[0];\nconst {useMDXComponents: _provideComponents} = arguments[0];\nfunction _createMdxContent(props) {\n const _components = {\n code: \"code\",\n p: \"p\",\n ..._provideComponents(),\n ...props.components\n };\n return _jsxs(_components.p, {\n children: [\"Model cost of one decision’s evaluations and previews over a window; reads only. What the decision’s evaluations cost over a window, for the key’s organization and environment. Amounts are US dollars in micros (\", _jsx(_components.code, {\n children: \"usd_micros\"\n }), \": millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor’s published price, plus an estimate for calls we couldn’t price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as \", _jsx(_components.code, {\n children: \"estimated_usd_micros\"\n }), \"; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in \", _jsx(_components.code, {\n children: \"other_spend\"\n }), \", outside the per-evaluation numbers, and \", _jsx(_components.code, {\n children: \"total\"\n }), \" adds everything recorded. Per-request \", _jsx(_components.code, {\n children: \"cost\"\n }), \" on evaluate and import_examples is reported cost only. \", _jsx(_components.code, {\n children: \"since\"\n }), \" (inclusive) and \", _jsx(_components.code, {\n children: \"until\"\n }), \" (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).\"]\n });\n}\nfunction MDXContent(props = {}) {\n const {wrapper: MDXLayout} = {\n ..._provideComponents(),\n ...props.components\n };\n return MDXLayout ? _jsx(MDXLayout, {\n ...props,\n children: _jsx(_createMdxContent, {\n ...props\n })\n }) : _createMdxContent(props);\n}\nreturn {\n default: MDXContent\n};\n","frontmatter":{},"scope":{}},"pageType":"default","mdx":{"mdxSource":{"compiledSource":"\"use strict\";const{Fragment:_Fragment,jsx:_jsx}=arguments[0];const{useMDXComponents:_provideComponents}=arguments[0];function _createMdxContent(props){return _jsx(_Fragment,{})}function MDXContent(props={}){const{wrapper:MDXLayout}={..._provideComponents(),...props.components};return MDXLayout?_jsx(MDXLayout,{...props,children:_jsx(_createMdxContent,{...props})}):_createMdxContent(props)}return{default:MDXContent}","frontmatter":{},"scope":{"config":{},"pageMetadata":{"title":"Get a decision's model cost, per evaluation and in total","description":"Model cost of one decision's evaluations and previews over a window; reads only. What the decision's evaluations cost over a window, for the key's organization and environment. Amounts are US dollars in micros (`usd_micros`: millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor's published price, plus an estimate for calls we couldn't price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as `estimated_usd_micros`; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in `other_spend`, outside the per-evaluation numbers, and `total` adds everything recorded. Per-request `cost` on evaluate and import_examples is reported cost only. `since` (inclusive) and `until` (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/usage","href":"/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total","autogeneratedByOpenApi":true}}},"mdxSourceWithNoJs":null},"mdxExtracts":{"tableOfContents":[],"codeExamples":{}},"jsLinks":[],"openApiReferenceData":{"operation":{"operationId":"getUsage","x-mcp-annotations":{"readOnlyHint":true,"openWorldHint":false},"tags":["usage"],"security":["7a4a00bd-79d5-4d54-9cc3-7c96c0685929"],"summary":"Get a decision's model cost, per evaluation and in total","description":"Model cost of one decision's evaluations and previews over a window; reads only. What the decision's evaluations cost over a window, for the key's organization and environment. Amounts are US dollars in micros (`usd_micros`: millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor's published price, plus an estimate for calls we couldn't price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as `estimated_usd_micros`; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in `other_spend`, outside the per-evaluation numbers, and `total` adds everything recorded. Per-request `cost` on evaluate and import_examples is reported cost only. `since` (inclusive) and `until` (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).","parameters":["8cc311b3-4b71-4932-8f87-52d0470d518b","67d21b88-187c-48fe-9f88-b8c2761a13e9","5f29aef5-32b5-4f6f-a9ee-51801540b0a6"],"responses":{"200":"9f4422c5-6b42-4dfa-953c-081a68e5e018","400":"6a20625e-1131-409b-b2d9-675de4100aa3","401":"ea5c2ae2-589d-4a47-af98-6f365a7bda1e","403":"82c41538-528f-4c3f-99d3-dae83660b4e6","429":"3f476173-78cd-4fef-9349-af33f28adfcb","503":"9cbb4cb7-9487-4d5b-8c43-dd1a2e1f06c4"},"method":"get","type":"path","servers":["862a956d-1c4f-4606-bdd8-1be7c77f4c78"],"path":"/v1/decisions/{decision_id}/usage","baseUrlOptions":["https://api.moonbounce.ai"],"title":"Get a decision's model cost, per evaluation and in total","codeSamples":[],"requiredOnlyExamples":false,"requestExampleType":"generated","responseExampleType":"generated"},"dependencies":{"parameters":{"8cc311b3-4b71-4932-8f87-52d0470d518b":{"schema":{"type":"string","pattern":"^[a-z][a-z0-9_.-]{0,127}$","description":"A name you choose for this decision, such as `refund-exception`: a lowercase letter, then up to 127 of `a-z 0-9 _ . -`. Unique in your organization and shared by its test and production keys. The first registration or evaluation under a new one creates the decision.","isRequired":true,"uniqueKey":"","typeLabel":"string"},"required":true,"description":"A name you choose for this decision, such as `refund-exception`: a lowercase letter, then up to 127 of `a-z 0-9 _ . -`. Unique in your organization and shared by its test and production keys. The first registration or evaluation under a new one creates the decision.","name":"decision_id","in":"path"},"67d21b88-187c-48fe-9f88-b8c2761a13e9":{"schema":{"type":"string","format":"date-time","description":"Start of the window, inclusive. Default: `until` - 30 days.","isRequired":false,"uniqueKey":"","typeLabel":"string\u003cdate-time>"},"required":false,"description":"Start of the window, inclusive. Default: `until` - 30 days.","name":"since","in":"query"},"5f29aef5-32b5-4f6f-a9ee-51801540b0a6":{"schema":{"type":"string","format":"date-time","description":"End of the window, exclusive. Default: now.","isRequired":false,"uniqueKey":"","typeLabel":"string\u003cdate-time>"},"required":false,"description":"End of the window, exclusive. Default: now.","name":"until","in":"query"}},"responses":{"9f4422c5-6b42-4dfa-953c-081a68e5e018":{"description":"The decision's cost report","content":{"application/json":{"schema":{"type":"object","properties":{"decision_id":{"type":"string","pattern":"^[a-z][a-z0-9_.-]{0,127}$","description":"A name you choose for this decision, such as `refund-exception`: a lowercase letter, then up to 127 of `a-z 0-9 _ . -`. Unique in your organization and shared by its test and production keys. The first registration or evaluation under a new one creates the decision.","isRequired":true,"uniqueKey":"decision_id","typeLabel":"string"},"environment":{"type":"string","enum":["production","test"],"description":"The environment of the key that made the call: `production` or `test`. Evaluations, feedback, reviews and suggestions are separate per environment; decisions and their versions belong to the whole organization.","isRequired":true,"uniqueKey":"environment","typeLabel":"enum\u003cstring>"},"window":{"type":"object","properties":{"since":{"type":"string","format":"date-time","isRequired":true,"uniqueKey":"window.since","typeLabel":"string\u003cdate-time>"},"until":{"type":"string","format":"date-time","isRequired":true,"uniqueKey":"window.until","typeLabel":"string\u003cdate-time>"}},"required":["since","until"],"isRequired":true,"uniqueKey":"window","typeLabel":"object"},"evaluations":{"type":"array","items":{"type":"object","properties":{"model":{"type":"object","properties":{"profile":{"type":"string","description":"Every question's model and connector, as one opaque string. Compare it for equality (two runs are comparable when their profiles match); don't parse it.","isRequired":true,"uniqueKey":"evaluations.items.[INDEX].model.profile","typeLabel":"string"}},"required":["profile"],"additionalProperties":true,"description":"The model that answered, as its opaque profile.","x-moonbounce-sdk-known-fields":true,"isRequired":true,"uniqueKey":"evaluations.items.[INDEX].model","typeLabel":"object"},"assignment_mode":{"type":"string","isRequired":true,"uniqueKey":"evaluations.items.[INDEX].assignment_mode","typeLabel":"string"},"evaluations":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"evaluations.items.[INDEX].evaluations","typeLabel":"integer"},"uncached":{"type":"integer","minimum":0,"description":"Evaluations that called a model, answered or not; the rest were answered from the answer cache.","isRequired":true,"uniqueKey":"evaluations.items.[INDEX].uncached","typeLabel":"integer"},"model_calls":{"type":"integer","minimum":0,"description":"Upstream calls made, including ones answered with an error and ones abandoned at the deadline; `models[]` counts every attempt.","isRequired":true,"uniqueKey":"evaluations.items.[INDEX].model_calls","typeLabel":"integer"},"input_tokens":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"evaluations.items.[INDEX].input_tokens","typeLabel":"integer"},"output_tokens":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"evaluations.items.[INDEX].output_tokens","typeLabel":"integer"},"usd_micros":{"type":"object","properties":{"total":{"type":"number","minimum":0,"isRequired":true,"uniqueKey":"evaluations.items.[INDEX].usd_micros.total","typeLabel":"number"},"mean":{"type":"number","minimum":0,"isRequired":true,"uniqueKey":"evaluations.items.[INDEX].usd_micros.mean","typeLabel":"number"},"p50":{"type":"number","minimum":0,"isRequired":true,"uniqueKey":"evaluations.items.[INDEX].usd_micros.p50","typeLabel":"number"},"p95":{"type":"number","minimum":0,"isRequired":true,"uniqueKey":"evaluations.items.[INDEX].usd_micros.p95","typeLabel":"number"}},"required":["total","mean","p50","p95"],"description":"Per evaluation, in millionths of a US dollar: reported cost plus the estimate for its calls that reported no usage.","isRequired":true,"uniqueKey":"evaluations.items.[INDEX].usd_micros","typeLabel":"object"},"estimated_usd_micros":{"type":"number","minimum":0,"description":"The estimated part of `usd_micros.total`: calls that may have been billed but reported no usage.","isRequired":true,"uniqueKey":"evaluations.items.[INDEX].estimated_usd_micros","typeLabel":"number"}},"required":["model","assignment_mode","evaluations","uncached","model_calls","input_tokens","output_tokens","usd_micros","estimated_usd_micros"],"uniqueKey":"evaluations.items.[INDEX]","typeLabel":"object"},"description":"One group per `model.profile` and assignment mode, ordered by both. Spend whose evaluation is gone is grouped under the profile `unknown`, as is dry-run spend, which has no evaluation.","isRequired":true,"uniqueKey":"evaluations","typeLabel":"object[]"},"models":{"type":"array","items":{"type":"object","properties":{"resolved_model":{"type":"string","isRequired":true,"uniqueKey":"models.items.[INDEX].resolved_model","typeLabel":"string"},"adapter":{"type":"string","isRequired":true,"uniqueKey":"models.items.[INDEX].adapter","typeLabel":"string"},"calls":{"type":"integer","minimum":0,"description":"Call attempts, retries and failures included.","isRequired":true,"uniqueKey":"models.items.[INDEX].calls","typeLabel":"integer"},"failed":{"type":"integer","minimum":0,"description":"Attempts whose status is not `ok`.","isRequired":true,"uniqueKey":"models.items.[INDEX].failed","typeLabel":"integer"},"input_tokens":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"models.items.[INDEX].input_tokens","typeLabel":"integer"},"output_tokens":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"models.items.[INDEX].output_tokens","typeLabel":"integer"},"usd_micros":{"type":"number","minimum":0,"description":"Reported plus estimated.","isRequired":true,"uniqueKey":"models.items.[INDEX].usd_micros","typeLabel":"number"},"estimated_usd_micros":{"type":"number","minimum":0,"description":"The estimated part: calls that may have been billed but reported no usage.","isRequired":true,"uniqueKey":"models.items.[INDEX].estimated_usd_micros","typeLabel":"number"}},"required":["resolved_model","adapter","calls","failed","input_tokens","output_tokens","usd_micros","estimated_usd_micros"],"uniqueKey":"models.items.[INDEX]","typeLabel":"object"},"description":"One group per resolved model and adapter, from the per-call traces. Evaluations stored before traces existed and dry runs contribute none.","isRequired":true,"uniqueKey":"models","typeLabel":"object[]"},"other_spend":{"type":"array","items":{"type":"object","properties":{"kind":{"type":"string","description":"`uncommitted`: evaluations, dry runs, imported examples and preview runs whose models ran but which never committed (a failed evaluate, an example that failed, the loser of an idempotency race, a preview that failed). `generation`: suggestion generation's own replays and model call (its proposal preview is in `previews`). New kinds may appear.","isRequired":true,"uniqueKey":"other_spend.items.[INDEX].kind","typeLabel":"string"},"attempts":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"other_spend.items.[INDEX].attempts","typeLabel":"integer"},"model_calls":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"other_spend.items.[INDEX].model_calls","typeLabel":"integer"},"input_tokens":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"other_spend.items.[INDEX].input_tokens","typeLabel":"integer"},"output_tokens":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"other_spend.items.[INDEX].output_tokens","typeLabel":"integer"},"model_input_tokens":{"type":"integer","minimum":0,"description":"The suggestion writer's language model tokens, apart from the decision's model tokens.","isRequired":true,"uniqueKey":"other_spend.items.[INDEX].model_input_tokens","typeLabel":"integer"},"model_output_tokens":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"other_spend.items.[INDEX].model_output_tokens","typeLabel":"integer"},"usd_micros":{"type":"number","minimum":0,"description":"Reported plus estimated.","isRequired":true,"uniqueKey":"other_spend.items.[INDEX].usd_micros","typeLabel":"number"},"estimated_usd_micros":{"type":"number","minimum":0,"isRequired":true,"uniqueKey":"other_spend.items.[INDEX].estimated_usd_micros","typeLabel":"number"}},"required":["kind","attempts","model_calls","input_tokens","output_tokens","model_input_tokens","model_output_tokens","usd_micros","estimated_usd_micros"],"uniqueKey":"other_spend.items.[INDEX]","typeLabel":"object"},"description":"Spend that is not an evaluation, one group per kind, kept out of the per-evaluation numbers.","isRequired":true,"uniqueKey":"other_spend","typeLabel":"object[]"},"total":{"type":"object","properties":{"usd_micros":{"type":"number","minimum":0,"isRequired":true,"uniqueKey":"total.usd_micros","typeLabel":"number"},"estimated_usd_micros":{"type":"number","minimum":0,"isRequired":true,"uniqueKey":"total.estimated_usd_micros","typeLabel":"number"}},"required":["usd_micros","estimated_usd_micros"],"description":"Everything recorded above: evaluations, other spend and previews.","isRequired":true,"uniqueKey":"total","typeLabel":"object"},"previews":{"type":"object","properties":{"runs":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"previews.runs","typeLabel":"integer"},"questions":{"type":"integer","minimum":0,"description":"Questions the runs sent to a model (not cached); one model call can answer several.","isRequired":true,"uniqueKey":"previews.questions","typeLabel":"integer"},"input_tokens":{"type":"integer","minimum":0,"isRequired":true,"uniqueKey":"previews.input_tokens","typeLabel":"integer"},"usd_micros":{"type":"number","minimum":0,"description":"Reported plus estimated.","isRequired":true,"uniqueKey":"previews.usd_micros","typeLabel":"number"},"estimated_usd_micros":{"type":"number","minimum":0,"isRequired":true,"uniqueKey":"previews.estimated_usd_micros","typeLabel":"number"}},"required":["runs","questions","input_tokens","usd_micros","estimated_usd_micros"],"description":"Stored preview runs in the window (`mb test`, previews, and the one preview each generated suggestion runs), which write no evaluations. Generation's exploratory replays and model call are in `other_spend`, as is a preview run that stored nothing (`uncommitted`).","isRequired":true,"uniqueKey":"previews","typeLabel":"object"}},"required":["decision_id","environment","window","evaluations","models","other_spend","total","previews"],"uniqueKey":"","typeLabel":"object"},"examples":{"Example":{"title":"Example","value":{"decision_id":"\u003cstring>","environment":"production","window":{"since":"2023-11-07T05:31:56Z","until":"2023-11-07T05:31:56Z"},"evaluations":[{"model":{"profile":"\u003cstring>"},"assignment_mode":"\u003cstring>","evaluations":1,"uncached":1,"model_calls":1,"input_tokens":1,"output_tokens":1,"usd_micros":{"total":1,"mean":1,"p50":1,"p95":1},"estimated_usd_micros":1}],"models":[{"resolved_model":"\u003cstring>","adapter":"\u003cstring>","calls":1,"failed":1,"input_tokens":1,"output_tokens":1,"usd_micros":1,"estimated_usd_micros":1}],"other_spend":[{"kind":"\u003cstring>","attempts":1,"model_calls":1,"input_tokens":1,"output_tokens":1,"model_input_tokens":1,"model_output_tokens":1,"usd_micros":1,"estimated_usd_micros":1}],"total":{"usd_micros":1,"estimated_usd_micros":1},"previews":{"runs":1,"questions":1,"input_tokens":1,"usd_micros":1,"estimated_usd_micros":1}}}},"exampleType":"generated"}},"exampleType":"generated"},"6a20625e-1131-409b-b2d9-675de4100aa3":{"description":"Invalid request: `param` names the field at fault when one applies","content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"object","properties":{"type":{"type":"string","enum":["invalid_request","authentication","permission_denied","not_found","conflict","rate_limited","engine_failed","unavailable","internal"],"isRequired":true,"uniqueKey":"error.type","typeLabel":"enum\u003cstring>"},"message":{"type":"string","description":"For people; don't parse it.","isRequired":true,"uniqueKey":"error.message","typeLabel":"string"},"reason":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Set where a caller can act on it, one of the reasons in the ErrorReason schema. New reasons may be added: treat an unknown one by the status and `type`.","uniqueKey":"error.reason","typeLabel":"string"},"param":{"type":"string","description":"The request field at fault, as a dotted path (`attribute_values.region`, `claims.1.value`).","uniqueKey":"error.param","typeLabel":"string"},"details":{"type":"object","properties":{"issues":{"type":"array","items":{"type":"object","properties":{"param":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].param","typeLabel":"string"},"code":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Stable, extensible issue code; unknown codes still have a parameter and human-readable message.","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].code","typeLabel":"string"},"message":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].message","typeLabel":"string"}},"required":["param","code","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"error.details.issues.items.[INDEX]","typeLabel":"object"},"uniqueKey":"error.details.issues","typeLabel":"object[]"}},"additionalProperties":{"oneOf":[{}],"uniqueKey":"error.details.additionalProperties","typeLabel":"any"},"uniqueKey":"error.details","typeLabel":"object"}},"required":["type","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"isRequired":true,"uniqueKey":"error","typeLabel":"object"}},"required":["error"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"","typeLabel":"object"},"examples":{"Example":{"title":"Example","value":{"error":{"type":"invalid_request","message":"\u003cstring>","reason":"\u003cstring>","param":"\u003cstring>","details":{"issues":[{"param":"\u003cstring>","code":"\u003cstring>","message":"\u003cstring>"}]}}}}},"exampleType":"generated"}},"exampleType":"generated"},"ea5c2ae2-589d-4a47-af98-6f365a7bda1e":{"description":"Missing or invalid API key (reason KEY_INVALID)","content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"object","properties":{"type":{"type":"string","enum":["invalid_request","authentication","permission_denied","not_found","conflict","rate_limited","engine_failed","unavailable","internal"],"isRequired":true,"uniqueKey":"error.type","typeLabel":"enum\u003cstring>"},"message":{"type":"string","description":"For people; don't parse it.","isRequired":true,"uniqueKey":"error.message","typeLabel":"string"},"reason":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Set where a caller can act on it, one of the reasons in the ErrorReason schema. New reasons may be added: treat an unknown one by the status and `type`.","uniqueKey":"error.reason","typeLabel":"string"},"param":{"type":"string","description":"The request field at fault, as a dotted path (`attribute_values.region`, `claims.1.value`).","uniqueKey":"error.param","typeLabel":"string"},"details":{"type":"object","properties":{"issues":{"type":"array","items":{"type":"object","properties":{"param":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].param","typeLabel":"string"},"code":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Stable, extensible issue code; unknown codes still have a parameter and human-readable message.","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].code","typeLabel":"string"},"message":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].message","typeLabel":"string"}},"required":["param","code","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"error.details.issues.items.[INDEX]","typeLabel":"object"},"uniqueKey":"error.details.issues","typeLabel":"object[]"}},"additionalProperties":{"oneOf":[{}],"uniqueKey":"error.details.additionalProperties","typeLabel":"any"},"uniqueKey":"error.details","typeLabel":"object"}},"required":["type","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"isRequired":true,"uniqueKey":"error","typeLabel":"object"}},"required":["error"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"","typeLabel":"object"},"examples":{"Example":{"title":"Example","value":{"error":{"type":"invalid_request","message":"\u003cstring>","reason":"\u003cstring>","param":"\u003cstring>","details":{"issues":[{"param":"\u003cstring>","code":"\u003cstring>","message":"\u003cstring>"}]}}}}},"exampleType":"generated"}},"exampleType":"generated"},"82c41538-528f-4c3f-99d3-dae83660b4e6":{"description":"The key may not do this","content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"object","properties":{"type":{"type":"string","enum":["invalid_request","authentication","permission_denied","not_found","conflict","rate_limited","engine_failed","unavailable","internal"],"isRequired":true,"uniqueKey":"error.type","typeLabel":"enum\u003cstring>"},"message":{"type":"string","description":"For people; don't parse it.","isRequired":true,"uniqueKey":"error.message","typeLabel":"string"},"reason":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Set where a caller can act on it, one of the reasons in the ErrorReason schema. New reasons may be added: treat an unknown one by the status and `type`.","uniqueKey":"error.reason","typeLabel":"string"},"param":{"type":"string","description":"The request field at fault, as a dotted path (`attribute_values.region`, `claims.1.value`).","uniqueKey":"error.param","typeLabel":"string"},"details":{"type":"object","properties":{"issues":{"type":"array","items":{"type":"object","properties":{"param":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].param","typeLabel":"string"},"code":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Stable, extensible issue code; unknown codes still have a parameter and human-readable message.","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].code","typeLabel":"string"},"message":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].message","typeLabel":"string"}},"required":["param","code","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"error.details.issues.items.[INDEX]","typeLabel":"object"},"uniqueKey":"error.details.issues","typeLabel":"object[]"}},"additionalProperties":{"oneOf":[{}],"uniqueKey":"error.details.additionalProperties","typeLabel":"any"},"uniqueKey":"error.details","typeLabel":"object"}},"required":["type","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"isRequired":true,"uniqueKey":"error","typeLabel":"object"}},"required":["error"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"","typeLabel":"object"},"examples":{"Example":{"title":"Example","value":{"error":{"type":"invalid_request","message":"\u003cstring>","reason":"\u003cstring>","param":"\u003cstring>","details":{"issues":[{"param":"\u003cstring>","code":"\u003cstring>","message":"\u003cstring>"}]}}}}},"exampleType":"generated"}},"exampleType":"generated"},"3f476173-78cd-4fef-9349-af33f28adfcb":{"description":"RATE_LIMITED: retry after Retry-After seconds; QUOTA_EXCEEDED: details.reset_at gives the daily reset time (no Retry-After)","headers":{"Retry-After":{"schema":{"type":"string","description":"Seconds to wait before retrying, when waiting helps."},"required":false,"description":"Seconds to wait before retrying, when waiting helps."}},"content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"object","properties":{"type":{"type":"string","enum":["invalid_request","authentication","permission_denied","not_found","conflict","rate_limited","engine_failed","unavailable","internal"],"isRequired":true,"uniqueKey":"error.type","typeLabel":"enum\u003cstring>"},"message":{"type":"string","description":"For people; don't parse it.","isRequired":true,"uniqueKey":"error.message","typeLabel":"string"},"reason":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Set where a caller can act on it, one of the reasons in the ErrorReason schema. New reasons may be added: treat an unknown one by the status and `type`.","uniqueKey":"error.reason","typeLabel":"string"},"param":{"type":"string","description":"The request field at fault, as a dotted path (`attribute_values.region`, `claims.1.value`).","uniqueKey":"error.param","typeLabel":"string"},"details":{"type":"object","properties":{"issues":{"type":"array","items":{"type":"object","properties":{"param":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].param","typeLabel":"string"},"code":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Stable, extensible issue code; unknown codes still have a parameter and human-readable message.","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].code","typeLabel":"string"},"message":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].message","typeLabel":"string"}},"required":["param","code","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"error.details.issues.items.[INDEX]","typeLabel":"object"},"uniqueKey":"error.details.issues","typeLabel":"object[]"}},"additionalProperties":{"oneOf":[{}],"uniqueKey":"error.details.additionalProperties","typeLabel":"any"},"uniqueKey":"error.details","typeLabel":"object"}},"required":["type","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"isRequired":true,"uniqueKey":"error","typeLabel":"object"}},"required":["error"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"","typeLabel":"object"},"examples":{"Example":{"title":"Example","value":{"error":{"type":"invalid_request","message":"\u003cstring>","reason":"\u003cstring>","param":"\u003cstring>","details":{"issues":[{"param":"\u003cstring>","code":"\u003cstring>","message":"\u003cstring>"}]}}}}},"exampleType":"generated"}},"exampleType":"generated"},"9cbb4cb7-9487-4d5b-8c43-dd1a2e1f06c4":{"description":"Temporarily unavailable, with Retry-After (for example reason AUTH_UNAVAILABLE, ENGINE_UNAVAILABLE or STORE_UNAVAILABLE): retry with the same Idempotency-Key","headers":{"Retry-After":{"schema":{"type":"string","description":"Seconds to wait before retrying, when waiting helps."},"required":true,"description":"Seconds to wait before retrying, when waiting helps."}},"content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"object","properties":{"type":{"type":"string","enum":["invalid_request","authentication","permission_denied","not_found","conflict","rate_limited","engine_failed","unavailable","internal"],"isRequired":true,"uniqueKey":"error.type","typeLabel":"enum\u003cstring>"},"message":{"type":"string","description":"For people; don't parse it.","isRequired":true,"uniqueKey":"error.message","typeLabel":"string"},"reason":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Set where a caller can act on it, one of the reasons in the ErrorReason schema. New reasons may be added: treat an unknown one by the status and `type`.","uniqueKey":"error.reason","typeLabel":"string"},"param":{"type":"string","description":"The request field at fault, as a dotted path (`attribute_values.region`, `claims.1.value`).","uniqueKey":"error.param","typeLabel":"string"},"details":{"type":"object","properties":{"issues":{"type":"array","items":{"type":"object","properties":{"param":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].param","typeLabel":"string"},"code":{"type":"string","pattern":"^[A-Z][A-Z0-9_]+$","description":"Stable, extensible issue code; unknown codes still have a parameter and human-readable message.","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].code","typeLabel":"string"},"message":{"type":"string","isRequired":true,"uniqueKey":"error.details.issues.items.[INDEX].message","typeLabel":"string"}},"required":["param","code","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"error.details.issues.items.[INDEX]","typeLabel":"object"},"uniqueKey":"error.details.issues","typeLabel":"object[]"}},"additionalProperties":{"oneOf":[{}],"uniqueKey":"error.details.additionalProperties","typeLabel":"any"},"uniqueKey":"error.details","typeLabel":"object"}},"required":["type","message"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"isRequired":true,"uniqueKey":"error","typeLabel":"object"}},"required":["error"],"additionalProperties":true,"x-moonbounce-sdk-known-fields":true,"uniqueKey":"","typeLabel":"object"},"examples":{"Example":{"title":"Example","value":{"error":{"type":"invalid_request","message":"\u003cstring>","reason":"\u003cstring>","param":"\u003cstring>","details":{"issues":[{"param":"\u003cstring>","code":"\u003cstring>","message":"\u003cstring>"}]}}}}},"exampleType":"generated"}},"exampleType":"generated"}},"security":{"7a4a00bd-79d5-4d54-9cc3-7c96c0685929":{"bearerAuth":{"type":"http","scheme":"bearer","description":"An API key, sent as `Authorization: Bearer \u003ckey>`. Each operation lists the scope its key needs: `decisions:evaluate` (evaluate and read evaluations), `decisions:feedback` (your app's feedback) or `decisions:develop` (everything else, including owner feedback and the review queue). An operation listing no scope takes any scoped key. A key with no scope, or without the operation's, gets 403 INSUFFICIENT_SCOPE.","scopes":[],"schemeName":"bearerAuth"}}},"servers":{"862a956d-1c4f-4606-bdd8-1be7c77f4c78":{"url":"https://api.moonbounce.ai","description":"Production"}},"processedSecurityOptions":[{"schemes":[{"scheme":{"type":"http","scheme":"bearer","description":"An API key, sent as `Authorization: Bearer \u003ckey>`. Each operation lists the scope its key needs: `decisions:evaluate` (evaluate and read evaluations), `decisions:feedback` (your app's feedback) or `decisions:develop` (everything else, including owner feedback and the review queue). An operation listing no scope takes any scoped key. A key with no scope, or without the operation's, gets 403 INSUFFICIENT_SCOPE.","scopes":[],"schemeName":"bearerAuth"},"schema":{"title":"Bearer Auth","type":"string","isRequired":true,"description":"An API key, sent as `Authorization: Bearer \u003ckey>`. Each operation lists the scope its key needs: `decisions:evaluate` (evaluate and read evaluations), `decisions:feedback` (your app's feedback) or `decisions:develop` (everything else, including owner feedback and the review queue). An operation listing no scope takes any scoped key. A key with no scope, or without the operation's, gets 403 INSUFFICIENT_SCOPE.","format":"bearer","typeLabel":"string\u003cbearer>","deprecated":false},"schemeName":"bearerAuth","name":"Authorization"}],"title":"bearerAuth"}]},"originalFileLocation":"openapi.json"},"subdomain":"moonbounce","siteName":"Moonbounce Decisions API","title":"Get a decision's model cost, per evaluation and in total - Moonbounce Decisions API","navMaps":{"firstHrefInVersion":{},"firstHrefInLanguage":{}},"lastModified":"2026-11-07T03:22:57.510Z","originalFileLocation":"api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total.mdx"},"headHtml":"\u003cscript data-mint-head>(function(){var d=document.documentElement,p=null;if(!p){try{p=localStorage.getItem(\"isDarkMode\")}catch(e){}if(p==='true')p='dark';else if(p==='false')p='light';if(p!=='light'\u0026\u0026p!=='dark'\u0026\u0026p!=='system')p=\"system\"}var r=p==='system'?(matchMedia(\"(prefers-color-scheme: dark)\").matches?'dark':'light'):p;d.classList.remove(r==='dark'?'light':'dark');d.classList.add(r);d.setAttribute(\"data-theme-preference\",p)})();\u003c/script>\u003cmeta data-mint-head name=\"description\" content=\"Model cost of one decision\u0026#x27;s evaluations and previews over a window; reads only. What the decision\u0026#x27;s evaluations cost over a window, for the key\u0026#x27;s organization and environment. Amounts are US dollars in micros (usd_micros: millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor\u0026#x27;s published price, plus an estimate for calls we couldn\u0026#x27;t price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as estimated_usd_micros; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in other_spend, outside the per-evaluation numbers, and total adds everything recorded. Per-request cost on evaluate and import_examples is reported cost only. since (inclusive) and until (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).\">\u003cmeta data-mint-head name=\"application-name\" content=\"Moonbounce Decisions API\">\u003cmeta data-mint-head name=\"generator\" content=\"Mintlify\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon/android-chrome-192x192.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"apple-touch-icon\" type=\"image/png\" sizes=\"180x180\" href=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon/apple-touch-icon.png\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon/favicon-16x16.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon/favicon-32x32.png\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon/favicon.ico\" media=\"(prefers-color-scheme: light)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"192x192\" href=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon-dark/android-chrome-192x192.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"16x16\" href=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon-dark/favicon-16x16.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"icon\" type=\"image/png\" sizes=\"32x32\" href=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon-dark/favicon-32x32.png\" media=\"(prefers-color-scheme: dark)\">\u003clink data-mint-head rel=\"shortcut icon\" type=\"image/x-icon\" href=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon-dark/favicon.ico\" media=\"(prefers-color-scheme: dark)\">\u003cmeta data-mint-head property=\"og:title\" content=\"Get a decision\u0026#x27;s model cost, per evaluation and in total - Moonbounce Decisions API\">\u003cmeta data-mint-head property=\"og:description\" content=\"Model cost of one decision\u0026#x27;s evaluations and previews over a window; reads only. What the decision\u0026#x27;s evaluations cost over a window, for the key\u0026#x27;s organization and environment. Amounts are US dollars in micros (usd_micros: millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor\u0026#x27;s published price, plus an estimate for calls we couldn\u0026#x27;t price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as estimated_usd_micros; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in other_spend, outside the per-evaluation numbers, and total adds everything recorded. Per-request cost on evaluate and import_examples is reported cost only. since (inclusive) and until (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).\">\u003cmeta data-mint-head property=\"og:site_name\" content=\"Moonbounce Decisions API\">\u003cmeta data-mint-head property=\"og:url\" content=\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total\">\u003cmeta data-mint-head property=\"og:type\" content=\"website\">\u003cmeta data-mint-head property=\"og:image\" content=\"https://moonbounce.mintlify.site/_mintlify/api/og/v2?division=usage\u0026amp;title=Get+a+decision%27s+model+cost%2C+per+evaluation+and+in+total\u0026amp;description=Model+cost+of+one+decision%27s+evaluations+and+previews+over+a+window%3B+reads+only.+What+the+decision%27s+evaluations+cost+over+a+window%2C+for+the+key%27s+organization+\u0026amp;theme=e6d1608244ab860cac0ff47e\u0026amp;signature=a25fa70cd91198c1d4ba8ceb7514233d211f54c1fd4d7e58daa3de14a91b7f5d\">\u003cmeta data-mint-head property=\"og:image:width\" content=\"1200\">\u003cmeta data-mint-head property=\"og:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"twitter:card\" content=\"summary_large_image\">\u003cmeta data-mint-head name=\"twitter:title\" content=\"Get a decision\u0026#x27;s model cost, per evaluation and in total - Moonbounce Decisions API\">\u003cmeta data-mint-head name=\"twitter:description\" content=\"Model cost of one decision\u0026#x27;s evaluations and previews over a window; reads only. What the decision\u0026#x27;s evaluations cost over a window, for the key\u0026#x27;s organization and environment. Amounts are US dollars in micros (usd_micros: millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor\u0026#x27;s published price, plus an estimate for calls we couldn\u0026#x27;t price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as estimated_usd_micros; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in other_spend, outside the per-evaluation numbers, and total adds everything recorded. Per-request cost on evaluate and import_examples is reported cost only. since (inclusive) and until (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).\">\u003cmeta data-mint-head name=\"twitter:image\" content=\"https://moonbounce.mintlify.site/_mintlify/api/og/v2?division=usage\u0026amp;title=Get+a+decision%27s+model+cost%2C+per+evaluation+and+in+total\u0026amp;description=Model+cost+of+one+decision%27s+evaluations+and+previews+over+a+window%3B+reads+only.+What+the+decision%27s+evaluations+cost+over+a+window%2C+for+the+key%27s+organization+\u0026amp;theme=e6d1608244ab860cac0ff47e\u0026amp;signature=a25fa70cd91198c1d4ba8ceb7514233d211f54c1fd4d7e58daa3de14a91b7f5d\">\u003cmeta data-mint-head name=\"twitter:image:width\" content=\"1200\">\u003cmeta data-mint-head name=\"twitter:image:height\" content=\"630\">\u003cmeta data-mint-head name=\"msapplication-config\" content=\"/mintlify-assets/_mintlify/favicons/moonbounce/Pq6Jhs_BrzDTLcf2/_generated/favicon/browserconfig.xml\">\u003cmeta data-mint-head name=\"apple-mobile-web-app-title\" content=\"Moonbounce Decisions API\">\u003cmeta data-mint-head name=\"msapplication-TileColor\" content=\"#1D5AB5\">\u003clink data-mint-head rel=\"canonical\" href=\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total\">\u003clink data-mint-head rel=\"alternate\" type=\"application/xml\" href=\"/sitemap.xml\">\u003clink data-mint-head rel=\"alternate\" type=\"text/markdown\" href=\"/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total.md\">\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@graph\":[{\"@type\":\"Organization\",\"@id\":\"https://docs.moonbounce.ai/#organization\",\"name\":\"Moonbounce Decisions API\",\"url\":\"https://docs.moonbounce.ai\",\"logo\":{\"@type\":\"ImageObject\",\"url\":\"https://mintcdn.com/moonbounce/mWuXGW-nUJSEdABp/logo/lockup-light.svg?fit=max\u0026auto=format\u0026n=mWuXGW-nUJSEdABp\u0026q=85\u0026s=367a5dedb5799a16c5737d136af68dc5\"}},{\"@type\":\"WebSite\",\"@id\":\"https://docs.moonbounce.ai#website\",\"name\":\"Moonbounce Decisions API\",\"url\":\"https://docs.moonbounce.ai\",\"publisher\":{\"@id\":\"https://docs.moonbounce.ai/#organization\"}},{\"@type\":\"WebPage\",\"@id\":\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total#webpage\",\"url\":\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total\",\"name\":\"Get a decision's model cost, per evaluation and in total\",\"description\":\"Model cost of one decision's evaluations and previews over a window; reads only. What the decision's evaluations cost over a window, for the key's organization and environment. Amounts are US dollars in micros (usd_micros: millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor's published price, plus an estimate for calls we couldn't price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as estimated_usd_micros; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in other_spend, outside the per-evaluation numbers, and total adds everything recorded. Per-request cost on evaluate and import_examples is reported cost only. since (inclusive) and until (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).\",\"dateModified\":\"2026-11-07T03:22:57.510Z\",\"isPartOf\":{\"@id\":\"https://docs.moonbounce.ai#website\"},\"breadcrumb\":{\"@id\":\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total#breadcrumb\"}},{\"@type\":\"BreadcrumbList\",\"@id\":\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Endpoints\",\"item\":\"https://docs.moonbounce.ai/api-reference/health/health-check\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Get a decision's model cost, per evaluation and in total\",\"item\":\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total\"}]},{\"@type\":[\"TechArticle\",\"APIReference\"],\"@id\":\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total#apireference\",\"headline\":\"Get a decision's model cost, per evaluation and in total\",\"name\":\"Get a decision's model cost, per evaluation and in total\",\"description\":\"Model cost of one decision's evaluations and previews over a window; reads only. What the decision's evaluations cost over a window, for the key's organization and environment. Amounts are US dollars in micros (usd_micros: millionths of a dollar). Costs are what the models reported, priced by each adapter from the vendor's published price, plus an estimate for calls we couldn't price from a vendor report (no usage reported, or a suggestion-writer model with no listed price), broken out as estimated_usd_micros; cache hits cost nothing. Evaluations that never committed and suggestion generation (its replays and model call) are in other_spend, outside the per-evaluation numbers, and total adds everything recorded. Per-request cost on evaluate and import_examples is reported cost only. since (inclusive) and until (exclusive) are read to the millisecond and default to the last 30 days ending now; the window may span at most 366 days. A decision with no traffic in the window answers 200 with empty groups. The web session may not read it (403).\",\"url\":\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total\",\"mainEntityOfPage\":{\"@id\":\"https://docs.moonbounce.ai/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total#webpage\"},\"dateModified\":\"2026-11-07T03:22:57.510Z\",\"publisher\":{\"@id\":\"https://docs.moonbounce.ai/#organization\"},\"isPartOf\":{\"@id\":\"https://docs.moonbounce.ai#website\"}}]}\u003c/script>\u003cscript data-mint-head type=\"application/ld+json\">{\"@context\":\"https://schema.org\",\"@type\":\"WebSite\",\"name\":\"Moonbounce Decisions API\",\"creator\":{\"@type\":\"Organization\",\"name\":\"Mintlify\",\"url\":\"https://mintlify.com\"}}\u003c/script>","siteName":"Moonbounce Decisions API","nav":{"global":null,"tabs":[{"tab":"Guides","pages":[{"title":"Guides","href":""}]},{"tab":"API reference","groups":[{"group":"Overview","pages":[{"title":"API reference overview","href":"/reference/overview"}]},{"group":"Endpoints","pages":[{"group":"health","pages":[{"title":"Health check","deprecated":null,"version":null,"openapi":"/openapi.json get /health","href":"/api-reference/health/health-check"}]},{"group":"decisions","pages":[{"title":"Validate a decision file","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/validate","href":"/api-reference/decisions/validate-a-decision-file"},{"title":"List decisions","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions","href":"/api-reference/decisions/list-decisions"},{"title":"Register a decision's version","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/decisions","href":"/api-reference/decisions/register-a-decisions-version"},{"title":"Get a version","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/versions/{ref}","href":"/api-reference/decisions/get-a-version"},{"title":"Get a decision","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}","href":"/api-reference/decisions/get-a-decision"},{"title":"List a decision's versions","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/versions","href":"/api-reference/decisions/list-a-decisions-versions"}]},{"group":"models","pages":[{"title":"List the models a decision can run on","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/models","href":"/api-reference/models/list-the-models-a-decision-can-run-on"},{"title":"Get the model a decision runs on","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/model","href":"/api-reference/models/get-the-model-a-decision-runs-on"},{"title":"Choose the model a decision runs on","deprecated":null,"version":null,"openapi":"/openapi.json put /v1/decisions/{decision_id}/model","href":"/api-reference/models/choose-the-model-a-decision-runs-on"}]},{"group":"evaluate","pages":[{"title":"Run a version over many items","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/decisions/{decision_id}/runs","href":"/api-reference/evaluate/run-a-version-over-many-items"},{"title":"Evaluate an item","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/evaluate","href":"/api-reference/evaluate/evaluate-an-item"},{"title":"Get a past evaluation","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/evaluations/{evaluation_id}","href":"/api-reference/evaluate/get-a-past-evaluation"},{"title":"List a decision's evaluations","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/evaluations","href":"/api-reference/evaluate/list-a-decisions-evaluations"}]},{"group":"objective","pages":[{"title":"Sweep a cut over a run's answers","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/decisions/{decision_id}/cut-sweeps","href":"/api-reference/objective/sweep-a-cut-over-a-runs-answers"},{"title":"Judge results under a decision's objective","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/decisions/{decision_id}/loss-reports","href":"/api-reference/objective/judge-results-under-a-decisions-objective"},{"title":"Get what a decision optimizes for","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/objective","href":"/api-reference/objective/get-what-a-decision-optimizes-for"},{"title":"Set what a decision optimizes for","deprecated":null,"version":null,"openapi":"/openapi.json put /v1/decisions/{decision_id}/objective","href":"/api-reference/objective/set-what-a-decision-optimizes-for"}]},{"group":"feedback","pages":[{"title":"List a decision's labeled cases","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/cases","href":"/api-reference/feedback/list-a-decisions-labeled-cases"},{"title":"Submit feedback on evaluations or items","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/feedback","href":"/api-reference/feedback/submit-feedback-on-evaluations-or-items"},{"title":"Get a feedback submission as stored","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/feedback/{feedback_id}","href":"/api-reference/feedback/get-a-feedback-submission-as-stored"},{"title":"Export a decision's feedback as training data","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/feedback","href":"/api-reference/feedback/export-a-decisions-feedback-as-training-data"},{"title":"Import labeled examples","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/decisions/{decision_id}/examples","href":"/api-reference/feedback/import-labeled-examples"}]},{"group":"review","pages":[{"title":"Fill the review queue","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/review/items/fill","href":"/api-reference/review/fill-the-review-queue"},{"title":"List review items","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/review/items","href":"/api-reference/review/list-review-items"},{"title":"Get a review item","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/review/items/{review_item_id}","href":"/api-reference/review/get-a-review-item"},{"title":"Get the structure a review item was decided with","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/review/items/{review_item_id}/configuration","href":"/api-reference/review/get-the-structure-a-review-item-was-decided-with"},{"title":"Mark a review item as shown","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/review/items/{review_item_id}/shown","href":"/api-reference/review/mark-a-review-item-as-shown"},{"title":"Submit a review","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/review/items/{review_item_id}/submit","href":"/api-reference/review/submit-a-review"},{"title":"Withdraw a review answer","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/review/items/{review_item_id}/withdraw","href":"/api-reference/review/withdraw-a-review-answer"},{"title":"Change your own earlier review answer","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/review/items/{review_item_id}/change","href":"/api-reference/review/change-your-own-earlier-review-answer"},{"title":"Skip a review item","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/review/items/{review_item_id}/skip","href":"/api-reference/review/skip-a-review-item"},{"title":"Add the reason for a blind disagreement","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/review/items/{review_item_id}/reason","href":"/api-reference/review/add-the-reason-for-a-blind-disagreement"}]},{"group":"suggestions","pages":[{"title":"List suggestions for a decision","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/suggestions","href":"/api-reference/suggestions/list-suggestions-for-a-decision"},{"title":"Generate a suggestion on demand","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/decisions/{decision_id}/suggestions","href":"/api-reference/suggestions/generate-a-suggestion-on-demand"},{"title":"Get a suggestion","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/suggestions/{suggestion_id}","href":"/api-reference/suggestions/get-a-suggestion"},{"title":"Mark a suggestion pulled or rejected","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/suggestions/{suggestion_id}/status","href":"/api-reference/suggestions/mark-a-suggestion-pulled-or-rejected"},{"title":"Preview a structure change against past feedback","deprecated":null,"version":null,"openapi":"/openapi.json post /v1/decisions/{decision_id}/previews","href":"/api-reference/suggestions/preview-a-structure-change-against-past-feedback"},{"title":"Get the improvement loop's status","description":"Reports where the decision's improvement loop stands, and whether to stop: accepted suggestions with their evidence labels, review counts, spot-check agreement (on the version that last served production before the first acceptance vs on accepted candidates, by the version that served each production review) and the stop check: after `threshold` reviews with no suggestion that has a credible win (evidence labeled training_cases with more fixes than breaks on those cases, by more than the noise floor), stop and rethink. That evidence is in-sample (cases the generator may have seen); spot-check agreement is the forward measure. Counts the key's environment only: a test key's reviews, random stratum and suggestions, with no accepted suggestions and so no spot check (acceptance is production's).","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/loop","href":"/api-reference/suggestions/get-the-improvement-loops-status"}]},{"group":"usage","pages":[{"title":"Get a decision's model cost, per evaluation and in total","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/decisions/{decision_id}/usage","href":"/api-reference/usage/get-a-decisions-model-cost-per-evaluation-and-in-total"}]},{"group":"keys","pages":[{"title":"Identify the calling key or sign-in","description":"Who is calling: the organization, environment (production or test), key id, actor and scopes of this API key, or of the sign-in when an agent connects over OAuth (then key_id is an oauth: id, not a revocable key). Reads nothing and spends nothing; call it first to learn which environment your calls will read and write.","deprecated":null,"version":null,"openapi":"/openapi.json get /v1/whoami","href":"/api-reference/keys/identify-the-calling-key-or-sign-in"}]}]}]}]},"basePath":"","title":"Get a decision's model cost, per evaluation and in total - Moonbounce Decisions API","buildId":"dpl_8LJbrAiZvr1K98WQNZXCyY5AvT34","deploymentId":"dpl_8LJbrAiZvr1K98WQNZXCyY5AvT34","dynamics":["10e4515597","c2aa737661","2b790eda92","b0f84f53ff","a9bb46feb3"],"chunks":["BannerMarkdown-BcDCEkh6.js","dist-CwjSCXIK.js","lib-DuNMoZ05.js","lib-B8HbPgcC.js","clsx-eKJ4rcii.js","html-void-elements-mCSPHezU.js","katex-YMM-FMeD.js","marked.esm-CZWythHk.js","OpenApiReferenceProvider-i2a3QZ8E.js","utils-ChLwp8m0.js","cloneDeep-izs3Hzxb.js","_Uint8Array-BVIqJ90l.js","isObjectLike-C8vmzPEN.js","isArray-Dcu1dQ5t.js","utils-DRktVTDc.js","toString-BX-iyh8G.js","isSymbol-CSH9U2Gm.js","addUniqueKeysToSchema-CA2pEs4T.js","snippetPresets-ClQ6XrKD.js","style-to-object-BY3JEAdk.js","v4-DIgz8zy6.js","ApiExamples-Ct_Lv36y.js","isEqual-BfaiBbcl.js","usePlaygroundInputsStore-Cn2PYw9e.js","shallow-rkyymjXQ.js","getApiPlaygroundDisplay-BB9vkXtE.js","CodeSnippet-Bm5RU7m1.js","CodeSnippets-BgU9Deuz.js","Page-BUDYNlhG.js","getPastedJson-BD-6NNum.js","icon-8Z6tud2e.js","MethodPill-Tuzr4g3V.js","DuplicateIcon-0ceWFYhN.js","createIcon-FBXow_ST.js","DynamicMarkdown-CD8713Yy.js","SectionHeading-7zgzQbH-.js","axios-vUo_bRtp.js","Markdown-D7Ofw1oz.js","AssistantPageLink-9EK5IAXV.js"]}