{ "openapi": "3.0.1", "info": { "title": "Perplexity Ultra - Grounded JSON Extraction", "description": "Turn grounded web research into validated JSON with schema enforcement, source merging, confidence scoring, and batch processing.", "version": "1.0", "x-build-id": "RdJB2cecKrgf93hct" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/chriskelch77~perplexity-ultra/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-chriskelch77-perplexity-ultra", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/chriskelch77~perplexity-ultra/runs": { "post": { "operationId": "runs-sync-chriskelch77-perplexity-ultra", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/chriskelch77~perplexity-ultra/run-sync": { "post": { "operationId": "run-sync-chriskelch77-perplexity-ultra", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "mode" ], "properties": { "mode": { "title": "Execution Mode", "enum": [ "api", "batch" ], "type": "string", "description": "Choose 'api' to run a Standby server, or 'batch' to process a dataset.", "default": "api" }, "perplexityApiKey": { "title": "Perplexity API Key (BYOK)", "type": "string", "description": "Your Perplexity (or OpenRouter) API Key. This is stored securely." }, "modelChain": { "title": "Model Fallback Chain", "type": "array", "description": "If the first model fails, the Actor will automatically retry with the next in the list.", "items": { "type": "string" }, "default": [ "perplexity/sonar", "perplexity/sonar-reasoning" ] }, "policyPreset": { "title": "Policy Preset", "enum": [ "ultra-fast", "ultra-smart", "ultra-private", "ultra-json", "ultra-batch", "ultra-extract", "ultra-debug", "custom" ], "type": "string", "description": "Apply a predefined configuration profile. ultra-fast minimizes latency, ultra-smart enables repair + debug, ultra-private enforces PII masking and zero data retention, ultra-json enables strict JSON mode.", "default": "custom" }, "taskClass": { "title": "Task Class", "enum": [ "auto", "chat", "extraction", "classification", "reasoning", "embedding" ], "type": "string", "description": "Hint for the smart routing engine. 'auto' infers the task from the request shape.", "default": "auto" }, "route": { "title": "Target API Route", "enum": [ "chat", "responses", "embeddings" ], "type": "string", "description": "Which API route to target (usually chat for Perplexity models).", "default": "chat" }, "maxCostPerRunUsd": { "title": "Max Cost Per Run (USD)", "minimum": 0, "type": "number", "description": "Hard budget limit. The Actor will stop processing if this cost is exceeded.", "default": 5 }, "maxCostPerRequestUsd": { "title": "Max Cost Per Request (USD)", "minimum": 0, "type": "number", "description": "Maximum allowed cost for a single API request." }, "timeoutMs": { "title": "Timeout (ms)", "minimum": 1000, "type": "integer", "description": "Per-model timeout in milliseconds.", "default": 30000 }, "latencyTargetMs": { "title": "Latency Target (ms)", "minimum": 100, "type": "integer", "description": "Target latency hint for the routing engine. Lower values prefer faster models." }, "maxRetries": { "title": "Max Retries", "minimum": 0, "type": "integer", "description": "Maximum number of retries per request.", "default": 2 }, "enableExactCache": { "title": "Enable Exact Response Cache", "type": "boolean", "description": "If enabled, identical requests will be served from the internal cache (SHA-256 hash), saving tokens and money.", "default": true }, "cacheTtlSeconds": { "title": "Cache TTL (seconds)", "minimum": 1, "type": "integer", "description": "How long cached responses remain valid.", "default": 86400 }, "cacheNamespace": { "title": "Cache Namespace", "type": "string", "description": "Isolate cache entries by namespace. Useful for multi-tenant setups.", "default": "default" }, "enablePrefixCache": { "title": "Enable Prefix Cache", "type": "boolean", "description": "Enable advanced prefix-based caching for long prompts.", "default": true }, "userScopedCache": { "title": "User Scoped Cache", "type": "boolean", "description": "Isolate cache by user ID (if provided in request headers).", "default": true }, "jsonStrictMode": { "title": "Enable JSON Self-Healing", "type": "boolean", "description": "Automatically strip markdown and repair broken JSON syntax from the AI's output.", "default": true }, "jsonSchema": { "title": "JSON Schema", "type": "object", "description": "Validate LLM output against this JSON Schema. Used with JSON strict mode." }, "enableDeterministicRepair": { "title": "Enable Deterministic Repair", "type": "boolean", "description": "Try regex-based JSON repair before falling back to model-based repair.", "default": true }, "maxRepairAttempts": { "title": "Max Repair Attempts", "minimum": 0, "type": "integer", "description": "How many times to attempt repair before failing.", "default": 1 }, "enableRepairModel": { "title": "Enable Repair Model", "type": "boolean", "description": "Use a specialized model to fix JSON that deterministic repair cannot handle.", "default": false }, "repairModel": { "title": "Repair Model Name", "type": "string", "description": "Model to use for JSON self-healing if deterministic repair fails.", "default": "perplexity/sonar" }, "enableDebugArtifacts": { "title": "Enable Debug Artifacts", "type": "boolean", "description": "Store JSON parse/validation failure details for post-run inspection.", "default": true }, "piiMasking": { "title": "Enable PII Masking", "type": "boolean", "description": "Scrub emails and phone numbers before sending data to the AI provider.", "default": false }, "zdrOnly": { "title": "Zero Data Retention Only", "type": "boolean", "description": "Only route to providers that support zero data retention policies.", "default": false }, "redactLogs": { "title": "Redact Logs", "type": "boolean", "description": "Redact sensitive data from Actor logs.", "default": true }, "datasetId": { "title": "Target Dataset ID (Batch Mode Only)", "type": "string", "description": "The Apify Dataset ID containing the rows you want to process." }, "requestTemplate": { "title": "Request Template (Batch Mode Only)", "type": "object", "description": "The Perplexity payload template. Use {{fieldName}} to inject data from your dataset." }, "inputMapping": { "title": "Input Field Mapping", "type": "object", "description": "Advanced mapping of dataset fields to template variables." }, "sampleSize": { "title": "Batch Sample Size", "minimum": 1, "type": "integer", "description": "Process only the first N rows (useful for testing).", "default": 10 }, "deadLetterDatasetId": { "title": "Dead Letter Dataset ID", "type": "string", "description": "Failed batch rows are pushed to this dataset for inspection." }, "webhookUrl": { "title": "Completion Webhook URL", "type": "string", "description": "URL to POST a summary to when batch processing completes." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }