{ "openapi": "3.1.0", "info": { "title": "LLM Cutover API", "version": "1.0.0", "description": "Check whether a cheaper model (Sage 2) agrees with your current LLM on your own samples, and what a confidence-routed hybrid would cost per month. Anonymous tier: 3 audits/day per IP, 10 samples, shared daily pool; no key needed. Full tier: send the pass token from a $49 full audit as a Bearer key (5 runs, 30 days, up to 500 samples). Docs: https://llmcutover.com/docs/", "contact": { "email": "contact@llmcutover.com", "url": "https://llmcutover.com/docs/" }, "termsOfService": "https://llmcutover.com/legal/" }, "servers": [ { "url": "https://api.llmcutover.com" } ], "components": { "securitySchemes": { "pass": { "type": "http", "scheme": "bearer", "description": "Full-audit pass token (shown after checkout on /full/). Optional: without it you get the anonymous tier." } } }, "paths": { "/api/v1/audit": { "post": { "operationId": "runCutoverAudit", "summary": "Run a cutover audit on your samples", "security": [ {}, { "pass": [] } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "mode", "samples", "current" ], "properties": { "mode": { "type": "string", "enum": [ "yesno", "extract" ], "description": "yesno: a yes/no decision per text. extract: fields pulled out of each text." }, "question": { "type": "string", "maxLength": 600, "description": "yesno only. The yes/no question your current model answers, e.g. \"Is this ticket about billing?\"" }, "fields": { "type": "object", "description": "extract only. Up to 12 fields: {\"name\": {\"type\": \"string|number|integer|boolean|date|money\", \"definition\": \"...\"}}", "additionalProperties": { "type": "object", "properties": { "type": { "type": "string", "enum": [ "string", "number", "integer", "boolean", "date", "money" ] }, "definition": { "type": "string", "maxLength": 300 } } } }, "samples": { "description": "Real inputs with the answer your CURRENT model gave. Array of objects or a JSONL/CSV string. yesno: {\"text\",\"label\":\"yes|no\"}; extract: {\"text\",\"expected\":{...}}. Each text ≤ 4000 chars. Min 5. Max 10 anonymous, 25 free on the website, 500 yesno / 200 extract with a pass.", "oneOf": [ { "type": "array", "minItems": 5, "items": { "type": "object", "properties": { "text": { "type": "string" }, "label": { "type": "string", "enum": [ "yes", "no" ] }, "expected": { "type": "object" } }, "required": [ "text" ] } }, { "type": "string" } ] }, "current": { "type": "object", "description": "Your current model: {\"model\": \"\", \"effort\": \"\"} or custom prices {\"in\": USD per 1M input tokens, \"out\": USD per 1M output tokens}.", "properties": { "model": { "type": "string", "enum": [ "claude-fable-5.1", "claude-opus-5.5", "claude-sonnet-5.5", "claude-haiku-5.5", "gpt-6-astra", "gpt-5.6-sol", "gpt-6.1-sol", "gpt-6.1-terra", "gpt-5-mini", "gpt-6-luna", "gemini-4-argon", "gemini-3.8-flash", "gemini-3.1-flash-lite" ] }, "effort": { "type": "string" }, "in": { "type": "number", "minimum": 0, "maximum": 1000 }, "out": { "type": "number", "minimum": 0, "maximum": 1000 } } }, "target": { "type": "number", "enum": [ 0.95, 0.98, 0.99 ], "default": 0.98, "description": "Agreement you need on the calls the cheap model keeps." }, "usage": { "type": "object", "properties": { "monthlyCalls": { "type": "integer", "minimum": 0, "maximum": 1000000000, "default": 100000 }, "promptOverheadTokens": { "type": "integer", "minimum": 0, "maximum": 20000, "default": 400 }, "outputTokens": { "type": "integer", "minimum": 0, "maximum": 4000 }, "reasoningTokens": { "type": "integer", "minimum": 0, "maximum": 50000, "description": "Measured reasoning tokens per call, if you know them; otherwise estimated from effort." } } } } }, "example": { "mode": "yesno", "question": "Is this support ticket about billing?", "current": { "model": "gpt-6.1-sol", "effort": "medium" }, "usage": { "monthlyCalls": 200000 }, "samples": [ { "text": "I was charged twice this month", "label": "yes" }, { "text": "App crashes on login", "label": "no" }, { "text": "Refund for my last invoice?", "label": "yes" }, { "text": "How do I export my data", "label": "no" }, { "text": "Card declined at checkout", "label": "yes" } ] } } } }, "responses": { "200": { "description": "Audit report: agreement, routing threshold and coverage, monthly cost now vs hybrid.", "content": { "application/json": { "schema": { "type": "object", "properties": { "ok": { "type": "boolean" }, "mode": { "type": "string" }, "metrics": { "type": "object" }, "cost": { "type": "object" }, "fullCutover": { "type": "object" }, "sampleNote": { "type": [ "string", "null" ] }, "runsLeft": { "type": "integer" } } } } } }, "401": { "description": "Pass token invalid or expired.", "content": { "application/problem+json": { "schema": { "type": "object", "properties": { "type": { "type": "string" }, "title": { "type": "string" }, "status": { "type": "integer" }, "retry_after": { "type": "integer" } } } } } }, "413": { "description": "Body too large.", "content": { "application/problem+json": { "schema": { "type": "object", "properties": { "type": { "type": "string" }, "title": { "type": "string" }, "status": { "type": "integer" }, "retry_after": { "type": "integer" } } } } } }, "415": { "description": "Send application/json.", "content": { "application/problem+json": { "schema": { "type": "object", "properties": { "type": { "type": "string" }, "title": { "type": "string" }, "status": { "type": "integer" }, "retry_after": { "type": "integer" } } } } } }, "422": { "description": "Input problem (title says what).", "content": { "application/problem+json": { "schema": { "type": "object", "properties": { "type": { "type": "string" }, "title": { "type": "string" }, "status": { "type": "integer" }, "retry_after": { "type": "integer" } } } } } }, "429": { "description": "Rate limited: see Retry-After and RateLimit headers.", "content": { "application/problem+json": { "schema": { "type": "object", "properties": { "type": { "type": "string" }, "title": { "type": "string" }, "status": { "type": "integer" }, "retry_after": { "type": "integer" } } } } } }, "503": { "description": "Daily capacity used up or service paused: see Retry-After.", "content": { "application/problem+json": { "schema": { "type": "object", "properties": { "type": { "type": "string" }, "title": { "type": "string" }, "status": { "type": "integer" }, "retry_after": { "type": "integer" } } } } } } } } }, "/api/models": { "get": { "operationId": "listModels", "summary": "Price table, effort levels, limits", "responses": { "200": { "description": "Models and limits", "content": { "application/json": { "schema": { "type": "object" } } } } } } }, "/api/health": { "get": { "operationId": "health", "summary": "Liveness", "responses": { "200": { "description": "ok" } } } }, "/mcp": { "post": { "operationId": "mcp", "summary": "Remote MCP server (Streamable HTTP, JSON responses). Tool: run_cutover_audit.", "responses": { "200": { "description": "JSON-RPC 2.0 response" } } } } } }