# Firecrawl Whole Product Review

Source: [Firecrawl Whole Product Review](<https://www.sota2.com/benchmarks/firecrawl-product-review>)

Collection index: [llms.txt](<https://www.sota2.com/benchmarks/llms.txt>)

Data updated: 2026-11-17

Feature-by-feature results from website extraction, company and people lookups, and structured data tests.

## Results at a glance

Costs are for the tested runs. Dollar amounts come from AgentRouter receipts. Credit counts come from the Firecrawl plugin.

| Feature | Result | What we observed | Run cost |
| --- | --- | --- | --- |
| Scrape · exact URLs | 308/343 | Expected website details found | $0.96 |
| Crawl · homepages | 157/343 | Expected website details found | $4.70 |
| Company enrichment | 1/2 | Cloudflare matched. GitHub misidentified. | 4 credits |
| Named people | 2/2 | Correct executives and roles | 0 credits |
| People by role | 1 of 2 matched | CEO first, plus a CEO’s office profile | 4 credits |
| Alexandria | 3/4 | Exact npm version. Release date missing. | 5 credits |
| Search | #1 of 3 | Official React release page | 2 credits |
| Map | #2 of 5 | Official React release page | Unavailable |
| Browser interaction | Passed | One click revealed hidden text | Unavailable |
| Agent | 16/16 | Facts with supporting citations | $0.00 |
| Structured Scrape | 14/16 | Correct facts from exact URLs | $0.075 |

## Website extraction: exact URLs vs. homepages

Both runs come from our November 15 AgentRouter benchmark. We scored the same 343 expected details under two starting conditions.

At Momentic, Scrape found all seven prices from the exact URL. Crawl found zero from the homepage and spent nine of its ten pages on docs. Check which URLs Crawl visited before treating a missing price as absent from the site.

- [Website Task Review: coverage, timing and charges](<https://www.sota2.com/benchmarks/firecrawl-company-data>): Run data, inputs and scoring rules.

- [Compare tools on the same dataset](<https://www.sota2.com/benchmarks/company-website-evidence>): Shared company website benchmark.

| Measure | Scrape · exact URLs | Crawl · homepages |
| --- | --- | --- |
| What we supplied | 192 specific page URLs | 100 company homepages |
| How Firecrawl found pages | Read the supplied pages | Chose up to 10 pages per site within the 90-second test limit |
| Expected details found | 308/343 (89.8%) | 157/343 (45.8%) |
| Prices with billing units | 49/59 | 3/59 |
| Median / P95 time | 2.3 s / 5.0 s | 16.6 s / 31.6 s |
| Total run cost | $0.96 | $4.70 |

## Company enrichment

The returned domain matched both inputs, including the wrong entity. Check the company name before writing firmographics into a CRM.

- **Company match** — 1/2. Domains resolved correctly.

- **Source URL** — 0/2. Records included a source URL.

- **Test batch** — 4 credits. The Companies API.

- [Cloudflare: founding year and headquarters](<https://www.cloudflare.com/our-story/>): Confirms the Cloudflare fields.

- [GitHub: Dependabot acquisition](<https://github.blog/news-insights/company-news/one-million-dependabot-pull-requests-merged/>): Confirms Dependabot is a product GitHub acquired.

| Input | Company returned | Founded / headquarters | Provider time |
| --- | --- | --- | --- |
| cloudflare.com | Cloudflare · correct | 2009 / San Francisco | 351 ms |
| github.com | Dependabot · wrong entity | 2017 / San Francisco | 2,029 ms |

## People lookup by name

Given name and employer, DataLegion returned the right person, company and title for both executives. The batch cost 0 credits.

- [Cloudflare: Prince’s current role](<https://www.cloudflare.com/connect/speakers/>): Employer reference for the named lookup.

- [Microsoft: Nadella’s current role](<https://www.microsoft.com/investor/reports/ar26/index.html>): Employer reference for the named lookup.

| Input | Returned title | Provider time |
| --- | --- | --- |
| Matthew Prince + Cloudflare | Chief Executive Officer & Co-Founder | 230 ms |
| Satya Nadella + Microsoft | Chairman and Chief Executive Officer | 289 ms |

## People search by role

One FullEnrich query for CEO at cloudflare.com returned two profiles. One was Cloudflare’s CEO. The query cost 4 credits and the provider reported 1,178 ms.

The second profile’s title mentions the CEO but describes someone in the executive office. Check the full returned title before saving a contact as CEO.

- [Cloudflare: Matthew Prince is co-founder and CEO](<https://www.cloudflare.com/connect/speakers/>): Employer reference used to check the two returned records.

- [Run data: search inputs and both returned profiles](<https://www.sota2.com/benchmarks/firecrawl-product-review-runs-2026-11-17.json>): See the roleSearch run and query-level charge and duration.

| Rank | Person | Returned title | CEO match |
| --- | --- | --- | --- |
| 1 | Matthew Prince | CEO & Co-Founder | Yes |
| 2 | Name withheld | Executive Office of the Co-Founder & CEO, Matthew Prince | No · executive office |

## Alexandria: exact package lookup

This was one exact-version lookup. If you need the release date, check the publisher’s announcement.

- **Requested items** — 3/4. Name, version and registry URL. Date missing.

- **Discovery** — 0 credits. Two calls to find and inspect the npm capability.

- **Execution** — 5 credits. One npm lookup for react@19.0.0.

- [Returned npm record for React 19.0.0](<https://registry.npmjs.org/react/19.0.0>): The source URL in the provider response.

- [React release announcement: December 5, 2024](<https://react.dev/blog/2024/12/05/react-19>): Independent reference for the missing date.

## Search and Map

Both found the known announcement. Search used a dated query restricted to react.dev. Map used the domain and “react-19” as a keyword.

- **Search · React 19 release query** — #1 of 3. Official page found · 2 credits.

- **Map · react.dev** — #2 of 5. Official page found · cost unavailable.

- [Expected result: React’s release announcement](<https://react.dev/blog/2024/12/05/react-19>): The exact page used to check both returned lists.

## Browser interaction

Passed one click-and-wait test on a public demo. Per-call time and charge were unavailable.

- **Before clicking Start** — Hidden. “Hello World!” was in the DOM.

- **After clicking Start** — Visible. Firecrawl saw “Hello World!” on the page.

- **Session cleanup** — Closed. Stop call confirmed session ended.

- [Test fixture: dynamic loading demo](<https://the-internet.herokuapp.com/dynamic_loading/1>): Page where Start reveals the hidden text.

- [Run log: visibility check and session closure](<https://www.sota2.com/benchmarks/firecrawl-product-review-runs-2026-11-17.json>): See the Interact input and the before and after states.

## Structured answers and citations

The pilot covered three questions. Agent started from homepages and could cite any supporting official page. Scrape received exact URLs and its citations had to point to those pages.

- **Agent** — 16/16. Facts with supporting official citations · $0.00.

- **Structured Scrape** — 14/16. Correct facts · $0.075.

- **Structured Scrape citations** — 5/16. Facts with citations to the supplied page.

- [Pilot evidence: questions, citations and receipts](<https://www.sota2.com/benchmarks/company-website-structured-pilot-2026-11-15.json>): Returned facts and per-question scoring.

## Test scope

The four company, people and Alexandria checks reported 13 credits. The 55-second ChatGPT turn includes orchestration. The per-record times above are provider times. Website extraction and the structured-answer pilot use the November 15 AgentRouter results.

Untested in this review: Parse, Monitor, standalone Batch Scrape, developer, research, government and jobs workflows, and contact discovery or verification.

- [Firecrawl product profile](<https://www.sota2.com/products/firecrawl-firecrawl>): Product details and SOTA2 first-party research.

- [Firecrawl docs: feature inventory](<https://docs.firecrawl.dev/introduction>): Documented product features.

- [Firecrawl pricing: plans and credits](<https://www.firecrawl.dev/pricing>): Vendor pricing for interpreting credit-based charges.

## Test data

- [Firecrawl plugin runs · November 17 (JSON)](<https://www.sota2.com/benchmarks/firecrawl-product-review-runs-2026-11-17.json>): Test inputs and settings, selected responses, providers, timing and reported credits.

- [Website extraction runs · November 15 (JSON)](<https://www.sota2.com/benchmarks/company-website-retrieval-2026-11-15.json>): Exact URLs, homepage inputs, crawl limits and per-run results across the tools in the comparison.

- [Website extraction scorecard · November 15 (JSON)](<https://www.sota2.com/benchmarks/company-website-evidence-2026-11-15.json>): Expected field counts, coverage, timing and cost by tool, including both Firecrawl runs.

- [Structured answers pilot · November 15 (JSON)](<https://www.sota2.com/benchmarks/company-website-structured-pilot-2026-11-15.json>): Three questions, API settings, returned facts, citation checks and gateway receipts.

## Related SOTA2 benchmarks

- [Firecrawl Task Review: Collecting Company Data from Websites](<https://www.sota2.com/benchmarks/firecrawl-company-data>): The underlying Firecrawl tests for supplied page URLs and homepage crawls.

- [Best Tools for Collecting Company Data from Websites](<https://www.sota2.com/benchmarks/company-website-evidence>): A comparison of tools using the same website extraction dataset and scoring rules.

- [Context.dev API Feature Review](<https://www.sota2.com/benchmarks/context-dev-api>): A separate product review covering webpage extraction, G2 review parsing, PDF tables and monitoring.
