{ "openapi": "3.0.1", "info": { "title": "SEC EDGAR AI Scraper - LLM-ready filings, RAG chunks & signals", "description": "SEC EDGAR as LLM-ready data: section-aware Markdown, RAG chunks with stable IDs + SHA-256, XBRL facts, Form 4/13F, section diff, scored signals. Multi-event PPE. Pairs with sec-edgar-mcp.", "version": "0.0", "x-build-id": "nrCGQTuSU9vhRzGfB" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dominvo~sec-edgar-ai-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dominvo-sec-edgar-ai-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dominvo~sec-edgar-ai-scraper/runs": { "post": { "operationId": "runs-sync-dominvo-sec-edgar-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dominvo~sec-edgar-ai-scraper/run-sync": { "post": { "operationId": "run-sync-dominvo-sec-edgar-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Mode", "enum": [ "cik_ticker_map", "company_filings", "form_4_filings", "form_13d_filings", "form_13f_filings", "filing_markdown", "form_10q_filings", "form_d_filings", "form_8k_filings", "form_10k_filings", "xbrl_statements", "xbrl_facts", "xbrl_frames", "form_def14a_filings", "section_mda", "form_3_filings", "section_risk_factors", "form_5_filings", "form_13g_filings", "filing_text", "xbrl_metrics", "filings_index", "filings_feed", "filings_search", "section_icfr", "form_20f_filings", "form_s1_filings", "form_424b_prospectus", "form_s3_filings", "form_144_filings", "form_nport_filings", "form_6k_filings", "def14a_audit_fees", "def14a_exec_comp", "def14a_pay_vs_performance", "def14a_directors", "section_legal_proceedings", "section_business", "form_40f_filings", "form_atsn_filings", "section_subsidiaries", "form_ncsr_filings", "form_ncen_filings", "def14a_beneficial_owners", "form_npx_filings", "form_c_filings", "filing_chunks", "ai_importance", "section_diff", "ai_summary", "disclosure_compare", "peer_benchmark", "signal_pack", "insider_cluster", "lockup_expiration", "discrete_signals", "activist_clustering", "form_sd_disclosures", "form_25_notifications", "form_15_terminations", "form_8a_registrations", "form_reg_a_family", "form_14d9_recommendation", "form_to_tender", "form_s4_filings", "aaer_releases", "comment_letters", "administrative_proceedings", "litigation_releases", "form_adv_filings" ], "type": "string", "description": "Which mode to run. Catalog grows as new modes ship.", "default": "cik_ticker_map" }, "tickers": { "title": "Tickers", "type": "array", "description": "Stock tickers to look up (e.g. MDB, NET). Auto-resolved to CIK.", "default": [], "items": { "type": "string" } }, "ciks": { "title": "CIKs", "type": "array", "description": "Raw 10-digit CIKs (zero-padded or bare).", "default": [], "items": { "type": "string" } }, "companies": { "title": "Company names", "type": "array", "description": "Fuzzy company-name lookups. Only used by cik_ticker_map.", "default": [], "items": { "type": "string" } }, "domains": { "title": "Domains", "type": "array", "description": "Website domains (TLD stripped, treated as name hint). Only used by cik_ticker_map.", "default": [], "items": { "type": "string" } }, "date_from": { "title": "From date", "type": "string", "description": "Earliest filing date (YYYY-MM-DD). Optional. Used by filings modes." }, "date_to": { "title": "To date", "type": "string", "description": "Latest filing date (YYYY-MM-DD). Optional. Used by filings modes." }, "since_accession": { "title": "Resume since accession", "type": "string", "description": "Skip filings with accession number ≤ this value. For incremental resume." }, "forms": { "title": "Form types", "type": "array", "description": "Optional list of SEC form types to filter by (e.g. ['10-K', '8-K']). Used by ai_importance; if omitted, all forms are scored.", "default": [], "items": { "type": "string" } }, "output_format": { "title": "Output format", "enum": [ "json", "ndjson", "csv", "xlsx", "markdown" ], "type": "string", "description": "json streams to the default dataset. ndjson/csv/xlsx/markdown flush to the key-value store at end of run.", "default": "json" }, "form": { "title": "Form type", "type": "string", "description": "SEC form type to scope filing fetches (e.g. 10-K, 10-Q, S-1). Used by Tier 2 RAG/composite modes such as filing_chunks.", "default": "10-K" }, "sections": { "title": "Sections", "type": "array", "description": "Section keys to extract from each filing. Used by filing_chunks and similar Tier 2 modes. Common keys: risk_factors, mda, business, legal_proceedings, icfr.", "default": [ "risk_factors", "mda", "business" ], "items": { "type": "string" } }, "window_tokens": { "title": "Window tokens", "minimum": 1, "type": "integer", "description": "Token-window size for chunking section text. Used by filing_chunks.", "default": 1024 }, "overlap_tokens": { "title": "Overlap tokens", "minimum": 0, "type": "integer", "description": "Token overlap between adjacent chunks. Must be < window_tokens. Used by filing_chunks.", "default": 256 }, "section": { "title": "Section", "enum": [ "risk_factors", "mda", "business", "legal_proceedings", "icfr" ], "type": "string", "description": "Single section key to diff. Used by section_diff.", "default": "risk_factors" }, "mode_shape": { "title": "Output shape (section_diff)", "enum": [ "per_op", "per_section" ], "type": "string", "description": "section_diff: emit one record per diff op (per_op, default) or one bundle per filing pair (per_section).", "default": "per_op" }, "max_pairs": { "title": "Max filing pairs (section_diff)", "minimum": 1, "type": "integer", "description": "Cap on the number of adjacent (old, new) filing pairs diffed per issuer, newest first. Used by section_diff.", "default": 3 }, "model": { "title": "LLM model (ai_summary)", "type": "string", "description": "OpenRouter model slug for primary summarization. Used by ai_summary.", "default": "google/gemini-2.5-flash" }, "fallback_model": { "title": "Fallback LLM model (ai_summary)", "type": "string", "description": "OpenRouter model slug used as a fallback if the primary call fails. Used by ai_summary.", "default": "groq/llama-3.1-8b-instant" }, "openrouter_api_key": { "title": "OpenRouter API key (ai_summary)", "type": "string", "description": "OpenRouter API key. If omitted, the actor reads OPENROUTER_API_KEY from env. Required by ai_summary." }, "max_input_chars": { "title": "Max input characters (ai_summary)", "minimum": 1, "type": "integer", "description": "Maximum character length of the combined section text passed to the LLM. Used by ai_summary.", "default": 80000 }, "timeout": { "title": "LLM request timeout seconds (ai_summary)", "minimum": 1, "type": "integer", "description": "Timeout in seconds for each OpenRouter HTTP call. Used by ai_summary.", "default": 60 }, "lookback_quarters": { "title": "Lookback quarters (disclosure_compare / signal_pack)", "minimum": 1, "type": "integer", "description": "Trailing window in quarters (90 days each). Used by disclosure_compare (default 4 when date_from omitted) and signal_pack (default 8).", "default": 4 }, "signals": { "title": "Signal filter (signal_pack)", "type": "array", "description": "Subset of signal names to score. Omit to score all 12. Used by signal_pack.", "default": [], "items": { "type": "string" } }, "metrics": { "title": "Metrics (disclosure_compare / peer_benchmark)", "type": "array", "description": "Which side-by-side metrics to compute. Used by disclosure_compare (filing_cadence, insider_activity, eight_k_severity, activist_flag) and peer_benchmark (gross_margin, operating_margin, revenue_growth_yoy, roe, fcf_margin).", "default": [ "filing_cadence", "insider_activity", "eight_k_severity", "activist_flag" ], "items": { "type": "string" } }, "fiscal_year": { "title": "Fiscal year (xbrl_facts)", "type": "integer", "description": "Filter facts to a single fiscal year (e.g. 2024). Used by xbrl_facts." }, "window_days": { "title": "Window days (insider_cluster / activist_clustering)", "minimum": 1, "type": "integer", "description": "Rolling window (in days). Used by insider_cluster (default 60) and activist_clustering (default 90).", "default": 60 }, "min_filers": { "title": "Min filers per cluster (activist_clustering)", "minimum": 2, "type": "integer", "description": "Minimum number of unique 13D filers within the rolling window to qualify as a wolf-pack cluster. Used by activist_clustering.", "default": 2 }, "min_insiders": { "title": "Min insiders (insider_cluster)", "minimum": 2, "type": "integer", "description": "Minimum distinct insiders required to declare a cluster. Used by insider_cluster.", "default": 3 }, "direction": { "title": "Direction (insider_cluster)", "enum": [ "buy", "sell", "any" ], "type": "string", "description": "Restrict clusters by trade side: buy = non-sell codes only, sell = sell-side codes only, any = either (homogeneous per cluster). Used by insider_cluster.", "default": "any" }, "lookahead_days": { "title": "Lookahead days (lockup_expiration)", "minimum": 1, "type": "integer", "description": "Optional cap on how far in the future a projected lockup expiration date may fall. Records with expiration_date > today + lookahead_days are skipped. Used by lockup_expiration." }, "signal_types": { "title": "Signal type filter (discrete_signals)", "type": "array", "description": "Subset of discrete signal sub-types to emit. Omit (or leave empty) for all 7. Allowed values: late_filing, going_concern, material_weakness, restatement, auditor_change, cfo_change, ceo_change. Used by discrete_signals.", "default": [], "items": { "type": "string" } }, "variant": { "title": "Reg A+ variant (form_reg_a_family)", "enum": [ "1-A", "1-K", "1-SA", "1-U", "any" ], "type": "string", "description": "Which Reg A+ form variant to fetch. 'any' fetches all four. Used by form_reg_a_family.", "default": "any" }, "subtype": { "title": "SC TO subtype (form_to_tender)", "enum": [ "TO-I", "TO-T", "any" ], "type": "string", "description": "Which SC TO sub-type to fetch. 'any' fetches both. Used by form_to_tender.", "default": "any" }, "include_amendments": { "title": "Include amendments (form_s4_filings)", "type": "boolean", "description": "When true, also fetch S-4/A amendment filings alongside S-4 originals. Used by form_s4_filings.", "default": true }, "release_ids": { "title": "Release IDs (aaer_releases / litigation_releases)", "type": "array", "description": "Specific release IDs to fetch (e.g. 'AAER-4520' for aaer_releases, 'lr-25700' for litigation_releases). When omitted, all index rows matching the other filters are fetched.", "default": [], "items": { "type": "string" } }, "respondent_name": { "title": "Respondent name (aaer_releases / litigation_releases)", "type": "string", "description": "Case-insensitive substring match against the release index title. Used by aaer_releases and litigation_releases." }, "year": { "title": "Year (litigation_releases / administrative_proceedings)", "minimum": 1995, "type": "integer", "description": "Calendar year for the enforcement yearly archive. Defaults to current year when omitted. Used by litigation_releases and administrative_proceedings." }, "pair_window_days": { "title": "Pair window days (comment_letters)", "minimum": 1, "type": "integer", "description": "Maximum number of days after an UPLOAD (staff letter) within which a CORRESP (registrant response) is paired. Used by comment_letters.", "default": 90 }, "firm_names": { "title": "IAPD firm names (form_adv_filings)", "type": "array", "description": "Investment-adviser firm names to look up in IAPD. Each name resolves to one or more CRD numbers via IAPD firm search. Used by form_adv_filings.", "default": [], "items": { "type": "string" } }, "crd_numbers": { "title": "IAPD CRD numbers (form_adv_filings)", "type": "array", "description": "Direct IAPD CRD numbers to fetch firm reports for. Bypasses firm-name search. Used by form_adv_filings.", "default": [], "items": { "type": "string" } }, "include_disciplinary_only": { "title": "Disciplinary events only (form_adv_filings)", "type": "boolean", "description": "When true, emit one record per disclosure event instead of one summary record per firm. Used by form_adv_filings.", "default": false }, "file_numbers": { "title": "File numbers (administrative_proceedings)", "type": "array", "description": "Specific administrative-proceeding file numbers to fetch directly (e.g. '3-21800'). When set, the index is skipped. Used by administrative_proceedings.", "default": [], "items": { "type": "string" } }, "concepts": { "title": "XBRL concepts", "type": "array", "description": "XBRL concept names or patterns (e.g. ['Revenues', 'NetIncomeLoss']). Used by xbrl_facts (filter) and xbrl_frames (axis — at least one required). Empty = no filter on xbrl_facts.", "default": [], "items": { "type": "string" } }, "periods": { "title": "Periods (xbrl_frames)", "type": "array", "description": "XBRL Frames period codes — instant ('CY2024Q1I') or duration ('CY2024Q1', 'CY2024'). At least one required by xbrl_frames.", "default": [], "items": { "type": "string" } }, "units": { "title": "Units (xbrl_frames)", "type": "array", "description": "XBRL units of measure ('USD', 'shares', 'USD/shares'). Used by xbrl_frames.", "default": [ "USD" ], "items": { "type": "string" } }, "taxonomy": { "title": "Taxonomy (xbrl_frames)", "enum": [ "us-gaap", "ifrs-full", "dei", "srt" ], "type": "string", "description": "XBRL taxonomy ('us-gaap', 'ifrs-full', 'dei', 'srt'). Used by xbrl_frames.", "default": "us-gaap" }, "max_rows_per_frame": { "title": "Max rows per frame (xbrl_frames)", "minimum": 1, "type": "integer", "description": "Cap rows emitted per (concept, period, unit) frame. Used by xbrl_frames.", "default": 5000 }, "fiscal_periods": { "title": "Fiscal periods (xbrl_facts)", "type": "array", "description": "Filter facts to specific fiscal periods (['FY', 'Q1', 'Q2', 'Q3']). Empty = all periods. Used by xbrl_facts.", "default": [], "items": { "type": "string" } }, "statement_types": { "title": "Statement types (xbrl_facts)", "type": "array", "description": "Filter facts to specific statement types (['IncomeStatement', 'BalanceSheet', 'CashFlowStatement']). Empty = all. Used by xbrl_facts.", "default": [], "items": { "type": "string" } }, "max_facts": { "title": "Max facts per filing (xbrl_facts)", "minimum": 1, "type": "integer", "description": "Cap facts emitted per filing. Used by xbrl_facts.", "default": 5000 }, "transaction_codes": { "title": "Transaction codes (form_4_filings)", "type": "array", "description": "Form 4 transaction codes to keep (P=buy, S=sell, A=grant, M=exercise, F=tax withhold, G=gift, D=disposition, plus long-tail X/C/J/V/I/U). Empty = all codes. Used by form_4_filings.", "default": [], "items": { "type": "string" } }, "item_codes": { "title": "8-K item codes (form_8k_filings)", "type": "array", "description": "8-K Item numbers to keep (e.g. '2.02' earnings, '4.01' auditor change, '4.02' restatement, '5.02' exec change). Empty = all items. Used by form_8k_filings.", "default": [], "items": { "type": "string" } } } }, "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 } } } } } } } } } }