{ "openapi": "3.0.1", "info": { "title": "Dataset Cost Estimator — LLM Embedding Budget", "description": "Estimate USD token costs for an Apify dataset before RAG upsert. Compare chat & embedding models; optional fail-if-over-budget. No LLM API keys.", "version": "0.1", "x-build-id": "zzx9FjV23xacXwinH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fg-ei~dataset-llm-cost-estimator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fg-ei-dataset-llm-cost-estimator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fg-ei~dataset-llm-cost-estimator/runs": { "post": { "operationId": "runs-sync-fg-ei-dataset-llm-cost-estimator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fg-ei~dataset-llm-cost-estimator/run-sync": { "post": { "operationId": "run-sync-fg-ei-dataset-llm-cost-estimator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "reportName": { "title": "Report name", "type": "string", "description": "Friendly label shown in the Markdown REPORT and in the summary row (reportName).", "default": "Dataset LLM cost estimate" }, "items": { "title": "Inline JSON items", "type": "array", "description": "Paste rows here for quick tests (max 5,000 rows). Each object should contain text fields such as text or markdown. Mutually exclusive with Apify Dataset ID: clear this field before using a dataset." }, "datasetId": { "title": "Apify Dataset ID", "type": "string", "description": "ID (or name) of an existing Apify dataset you own, for example the default dataset of a Website Content Crawler run (open the run and copy its dataset ID). Read-only access is requested for this dataset only. Clear Inline JSON items when using this field." }, "allowRemoteFetch": { "title": "Allow remote dataset fetch", "type": "boolean", "description": "Must be enabled to read a dataset via Apify Dataset ID. Ignored for Inline JSON items.", "default": true }, "textFields": { "title": "Billable text fields", "type": "array", "description": "Field names whose values are concatenated as billable text for each row. Defaults cover common crawler outputs: text, markdown, content, body, pageContent, description.", "default": [ "text", "markdown", "content", "body", "pageContent", "description" ], "items": { "type": "string" } }, "chatModels": { "title": "Chat / completion models", "type": "array", "description": "Model IDs to price. Empty = defaults (gpt-4o-mini, gpt-4o, claude-haiku-4.5, gemini-2.0-flash). Supported: gpt-4o-mini, gpt-4o, gpt-4.1-mini, claude-haiku-4.5, claude-sonnet-4.6, gemini-2.0-flash, llama-3.3-70b. Unknown IDs fail validation.", "items": { "type": "string" } }, "embeddingModels": { "title": "Embedding models", "type": "array", "description": "Embedding model IDs to price. Empty = defaults (text-embedding-3-small, text-embedding-3-large). Supported: text-embedding-3-small, text-embedding-3-large, voyage-3-lite, voyage-3. Unknown IDs fail validation.", "items": { "type": "string" } }, "maxItems": { "title": "Max items (safety cap)", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Hard cap on rows analyzed. Rows beyond the cap are ignored. The rows-analyzed event is charged per analyzed row, so this also caps that charge (1,000 rows = $0.05).", "default": 1000 }, "assumedOutputTokensPerItem": { "title": "Assumed chat output tokens per item", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Assumed completion tokens per non-empty row when estimating chat cost. Use 0 to price input tokens only.", "default": 0 }, "budgetUsd": { "title": "Budget (USD)", "minimum": 0, "type": "number", "description": "Optional USD ceiling compared to the estimate selected in 'Budget comparison basis'. Leave empty for a report without gate." }, "budgetBasis": { "title": "Budget comparison basis", "enum": [ "cheapest_embedding", "most_expensive_embedding", "cheapest_chat_input", "most_expensive_chat_input" ], "type": "string", "description": "Which estimate is compared to Budget (USD).", "default": "cheapest_embedding" }, "failIfOverBudgetUsd": { "title": "Fail Actor run if over budget", "type": "boolean", "description": "When enabled (requires Budget), the Actor writes OUTPUT and REPORT, then fails the run with BUDGET_GATE_FAIL if the estimate exceeds the budget. Use as a CI / agent gate.", "default": false } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }