Factward vs Scrutinly
Factward
factward.comScrutinly
scrutinly.comSide by side
| Figure | Factward | Scrutinly |
|---|---|---|
| Price from | $9/mo | $12/mo |
| Free plan | Yes | Yes |
| Free trial | Yes | — |
| Open source | — | — |
| Web | Yes | Yes |
| API | Yes | — |
| Plans published | 2 | 3 |
| Spec score · AI Fact-Checking Tools | 8.9 (#2) | 7.5 (#13) |
| Verdicts | Reports classify claims as Supported, Conflicting Sources, Refuted, or Insufficient Evidence. | It rates claims as Supported, Unsupported, Mixed, or Satirical and links to sources used. |
| What it does | Factward checks individual factual claims in submitted material against web evidence and reports what is supported, unsupported, or unresolved. | Scrutinly fact-checks articles, claims, URLs, and images using Claude AI and provides source-backed verdicts. |
Plans
In their own words
Factward
Factward checks text, URLs, and PDFs by identifying factual claims and comparing them with web sources. Its AI model filters out opinions, predictions, and subjective statements, then retrieves up to five independent sources for each claim. Reports classify claims as Supported, Conflicting Sources, Refuted, or Insufficient Evidence, and include confidence, reasoning, linked sources, and a Trust Score. The service tracks when claims may have become stale and prompts users to check them again. A bookmarklet can send article text for review, and the Pro API can be used in a CMS or publishing pipeline. A beta Chrome extension highlights claims alongside verdicts and evidence, including when checking selected text from its context menu. Factward says submissions are used to produce results and are not sold or shared with third parties, though jobs and reports are stored in its database. Niche, paywalled, or very recent claims may lack evidence, and nuanced claims can be misinterpreted. The free plan allows two verifications per day; Pro costs $9 a month.
Scrutinly
Scrutinly is a web-based fact-checking service for articles, claims, URLs, social posts, and images. It extracts checkable statements from supplied text and evaluates each against current web sources. URL checking fetches the article directly, avoiding manual copying. Results classify claims as Supported, Unsupported, Mixed, or Satirical and provide links to the sources used. A stacked bar summarizes the proportions of Supported, Unsupported, and Mixed claims in a check. Image analysis is in beta: it estimates signs of AI generation or changed context, then gives a probability score and explanation; the service warns that these evaluations may be unreliable. Results remain in search history, and identical content can reuse cached output without consuming tokens. Security features listed by the site include two-factor authentication, PBKDF2 password hashing, and JWT sessions; searches are private to each account and not sold or shared. The Free plan costs nothing and includes 150,000 tokens. Pro costs $12 a month, while Max costs $49 a month.