{ "openapi": "3.0.1", "info": { "title": "Crunchbase - 139K Company DB, Funding, Investors & News ($8/1k)", "description": "Crunchbase four ways: live company scrape (Cloudflare handled), the Instant Database of 139K+ profiles served in seconds, 19,000+ VC firms with contacts at no surcharge, and Crunchbase News articles that name the companies they cover. Funding Monitor returns only NEW rounds per run. $8/1k.", "version": "1.0", "x-build-id": "8HyZK1p9WDZCsPHTU" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/memo23~crunchbase-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-memo23-crunchbase-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/memo23~crunchbase-scraper/runs": { "post": { "operationId": "runs-sync-memo23-crunchbase-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/memo23~crunchbase-scraper/run-sync": { "post": { "operationId": "run-sync-memo23-crunchbase-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", "properties": { "startUrls": { "title": "Crunchbase company URLs, slugs, or Discover search URLs", "type": "array", "description": "Paste any combination of:\n- **Full URL** — `https://www.crunchbase.com/organization/openai`\n- **Slug** — `openai`, `tesla-motors`\n- **Path** — `organization/stripe`\n- **Company name** — `Hugging Face`, `Mistral AI` (anything that cannot be a slug is looked up by name)\n- **Discover / saved-search URL** — `https://www.crunchbase.com/discover/funding_rounds/HASH`, one funding-round row per result with amounts and dates filled in\n\nEach company returns one clean structured row. A single word is read as a **slug** — to look a one-word name up by NAME instead (`Swish` has several companies), put it in **Company names** below.", "items": { "type": "string" } }, "companyNames": { "title": "Company names", "type": "array", "description": "Plain company names, one per line — `Stripe`, `Hugging Face`, `Swish`. Each is resolved through Crunchbase's own search and the best match is scraped exactly like a pasted URL. When several companies share the name, the run log lists the others with their URLs so you can pin the one you meant by slug. Optional.", "items": { "type": "string" } }, "companyListFile": { "title": "Bulk list file (TXT or CSV)", "type": "string", "description": "Upload a file, or link one, with one company per line — Crunchbase URLs, slugs, Discover URLs or plain names, mixed freely. For a CSV the first column is used and a header row is skipped. Duplicates are removed; up to 50,000 entries, still capped by **Max items**. Optional." }, "investorDatabase": { "title": "Use Startup Investors Database mode", "type": "boolean", "description": "Serve investor **firm** rows (one per VC / accelerator / angel / grant program) instead of company rows. Ordered by deal count (most active first), capped at **Max companies**. Auto-enabled if you set any investor filter below.", "default": false }, "investorQuery": { "title": "Investor name / description contains", "type": "string", "description": "Case-insensitive match on the firm name or description — e.g. `sequoia`, `climate`, `fintech`. Optional." }, "investorType": { "title": "Firm type", "enum": [ "Venture Capital Investor", "Seed / Early-Stage VC", "Accelerator", "Angel Investor", "Government / Grant Program", "Debt / Bank" ], "type": "string", "description": "Optional." }, "investorStage": { "title": "Investment stage", "enum": [ "Pre Seed Round", "Seed Round", "Series A", "Series B", "Series C", "Series D", "Venture Round", "Convertible Note", "Angel Round", "Grant", "Debt Financing", "Private Equity Round", "Corporate Round" ], "type": "string", "description": "Only firms observed participating in this round stage. Optional." }, "investorFocusArea": { "title": "Focus area (industry)", "type": "string", "description": "Industry the firm's portfolio invests in, e.g. `Artificial Intelligence (AI)`, `Biotechnology`, `FinTech`, `Health Care`, `E-Commerce`, `Energy`. Optional." }, "investorCountry": { "title": "Country", "type": "string", "description": "Matches the firm's HQ country **or** a country its portfolio invests into. Full English name, e.g. `United States`, `Germany`. Optional." }, "investorMinDeals": { "title": "Minimum deals", "minimum": 1, "type": "integer", "description": "Only firms with at least this many observed funding-round participations. Use `2+` to drop one-off investors. Optional." }, "instantDatabase": { "title": "Use Instant Database mode", "type": "boolean", "description": "Serve company rows from the database instead of live-scraping — same clean output shape, plus `source: \"instant-db\"`. Results are ordered by Crunchbase rank (best first) and capped at **Max companies**. Auto-enabled if you set any DB filter below.", "default": false }, "dbQuery": { "title": "Name / description contains", "type": "string", "description": "Case-insensitive match on the company name or description — e.g. `ai`, `fintech`, `logistics`. Optional." }, "dbCountry": { "title": "Country", "type": "string", "description": "Full country name, e.g. `United States`, `United Kingdom`, `Germany`, `India`. Optional." }, "dbEmployeeRange": { "title": "Employee range", "enum": [ "1-10", "11-50", "51-100", "101-250", "251-500", "501-1000", "1001-5000", "5001-10000", "10001+" ], "type": "string", "description": "Crunchbase headcount bucket. Optional." }, "dbOperatingStatus": { "title": "Operating status", "enum": [ "active", "closed" ], "type": "string", "description": "Optional." }, "roundsDatabase": { "title": "Use Funding Rounds mode", "type": "boolean", "description": "Serve **funding-round** rows (round name, type, amount in USD and original currency, announcement date, funded company) selected by the filters below. Switches on by itself as soon as you set any of them.\n\nPair it with **Only return items NEW since the previous run** and a daily schedule for a just-funded alert feed.", "default": false }, "roundType": { "title": "Round types", "type": "string", "description": "Comma-separated investment types. Most common in the archive: `grant` (5,060), `seed` (4,744), `pre_seed` (2,333), `series_unknown` (1,785), `series_a` (1,769), `debt_financing` (1,321), `non_equity_assistance` (1,098), `post_ipo_equity` (1,075), `post_ipo_debt` (850), `series_b` (795), `private_equity` (638), `angel` (498). Also valid: `series_c` … `series_g`, `convertible_note`, `corporate_round`, `equity_crowdfunding`, `secondary_market`, `undisclosed`. Optional." }, "minAmountUsd": { "title": "Minimum raised (USD)", "minimum": 0, "type": "integer", "description": "Only rounds that raised at least this much, in USD. Setting either amount bound excludes rounds with no disclosed figure — otherwise a \"$10M+\" filter would hand back undisclosed rounds too. Optional." }, "maxAmountUsd": { "title": "Maximum raised (USD)", "minimum": 0, "type": "integer", "description": "Only rounds at or below this amount, in USD. Optional." }, "announcedAfter": { "title": "Announced on or after", "type": "string", "description": "`YYYY-MM-DD`. Optional." }, "announcedBefore": { "title": "Announced on or before", "type": "string", "description": "`YYYY-MM-DD`. Optional." }, "roundCompany": { "title": "Funded company contains", "type": "string", "description": "Match on the funded company's name or Crunchbase slug — e.g. `stripe`, `mistral`. Archive-only: Crunchbase filters rounds by organization id rather than by name, so a run using this filter is never topped up live. Optional." }, "newsMode": { "title": "Use Crunchbase News mode", "type": "boolean", "description": "Serve **article** rows (title, URL, publish + modified dates, author, categories, tags, image, reading time and the linked companies) instead of scraping companies. Switches on by itself as soon as you fill in any News filter below.\n\nPair it with **Only return items NEW since the previous run** and a daily schedule to get a funding-story feed that never repeats itself.", "default": false }, "newsQuery": { "title": "Article contains", "type": "string", "description": "Free-text search across article titles and bodies — e.g. `raises`, `series b`, `layoffs`, `openai`. Optional." }, "newsCategory": { "title": "Categories", "type": "string", "description": "Comma-separated category slugs. The big ones: `venture` (5.5k articles), `startups` (4.4k), `business`, `ai`, `public`, `fintech-ecommerce`, `health-wellness-biotech`, `cybersecurity`, `clean-tech-and-energy`, `transportation`, `ma` (M&A), `ipo`, `crypto`, `seed`, `liquidity`, `diversity`. Optional — the full list is at news.crunchbase.com/wp-json/wp/v2/categories?per_page=100&_fields=slug" }, "newsTag": { "title": "Tags", "type": "string", "description": "Comma-separated tag slugs — e.g. `unicorn`. Optional." }, "newsDateFrom": { "title": "Published from", "type": "string", "description": "`YYYY-MM-DD` (or a full ISO timestamp). Only articles published on or after this date. Optional." }, "newsDateTo": { "title": "Published to", "type": "string", "description": "`YYYY-MM-DD` (or a full ISO timestamp). Only articles published on or before this date. Optional." }, "newsFullText": { "title": "Include full article text", "type": "boolean", "description": "Adds the whole article body as plain text. Off by default — bodies run to ~10,000 characters and most workflows only need the title, link and linked companies.", "default": false }, "fundingMonitor": { "title": "Only return items NEW since the previous run", "type": "boolean", "description": "When ON, each run compares its results against what previous runs **with the same input** already returned and emits only the NEW items — new **funding rounds** (per round id) on Discover searches, new **companies** (per permalink) otherwise. The very first run returns everything as the baseline; rows carry `fundingMonitorStatus: \"baseline\"` or `\"new\"`. Already-seen items are skipped and **not billed**. State is kept per input in this actor's own key-value store.", "default": false }, "rawMode": { "title": "Include raw Crunchbase cards", "type": "boolean", "description": "When ON, each row also includes the full raw `_rawCards` object (every Crunchbase data card, unprocessed) alongside the clean structured fields. Use this if you need a field the structured output doesn't surface. Default OFF (clean output only — ~10x smaller).", "default": false }, "maxItems": { "title": "Max companies", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Max company rows to emit across the whole run.", "default": 1000 }, "crunchbaseCookie": { "title": "Crunchbase session cookie", "type": "string", "description": "Optional. Paste your Crunchbase `Cookie` header from a logged-in browser session (DevTools → Network → any crunchbase.com request → Request Headers → Cookie). LOGGED-IN MODE unlocks the gated funding **amount**, **announced date** and **investors** on Discover results, lifts the 15-results-per-search cap (full pagination), and unlocks company funding totals during enrichment. Leave blank for anonymous mode (signal-only). Cookies expire — refresh periodically; this is a personal session, not for public/Store runs." }, "enrichEmails": { "title": "Enrich with contact emails (experimental, billed per email)", "type": "boolean", "description": "If enabled, finds a contact email for each result from its own website (or by discovering it from the name). Adds contactEmail + contactWebsite columns plus a detailed emailEnrichment object. Billed per contact email found; only charged when an email is returned, never for misses.", "default": false }, "qualifyByPayment": { "title": "💳 Qualify by payment (flag businesses that take money online)", "type": "boolean", "description": "Requires \"Enrich with contact emails\". Scans each business's website — reusing the pages already fetched for email discovery, so no extra cost or time — for payment processors and e-commerce platforms (Stripe, Shopify, PayPal, Paddle, Lemon Squeezy, WooCommerce, Square, Chargebee and more). Adds takesPayments (is this a real paying business?), paymentProcessors (which stack), stripeLiveKey (the public key if exposed) and paymentConfidence. Turn raw contacts into monetization-qualified leads. No extra charge — included with each enriched company.", "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 } } }, "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 } } } } } } } } } }