🚧 Purchasing isn't open yet — we're putting the finishing touches on payments and the browser extension.
Join the waitlist and we'll email you the moment it's ready →Stop reading blindly.
Start reading critically.
Every article you read is trying to shape how you think. BiasChecker gives you AI-powered lenses to see through spin, spot manipulation, and understand what's really being said — so you can form your own opinion, not someone else's.
Thirteen expert lenses on everything you read
Ever wish you could get an expert opinion on that article you just read? Now you can. Uncover hidden assumptions. See what the evidence actually supports and where the science gets speculative. Get a legal take, a moral perspective, or discover if history has seen this before — and how it played out. Each analysis goes beyond pointing out gaps to show what stronger, fairer coverage would look like.
Overview
Combines the other 12 lensesOne combined read, built from your other analyses
The consolidating lens: instead of reading the article yet again, it merges the results of the other lenses into a single trust read. You get a one-sentence verdict on what the piece is doing to its reader, plus the few cross-checked takeaways that matter. Building it costs one normal synthesis run; analyses you already have are always reused free, and if core analyses are missing it states how many it will run (each billed like any analysis) before anything starts.
Bias Detection
See what the author wants you to believe
Scans for 30 categories of bias including political, gender, racial, framing, and omission bias. Each finding includes evidence from the text.
Persuasion
Uncover hidden influence techniques
A focused 16-bias + 8-fallacy lens for spotting persuasion techniques in action — a deliberately narrower view than full Bias Detection.
Reveal Intent
Read between the lines
Exposes the gap between what a text literally says and what the author wants you to conclude. Cuts through spin to show the real message.
Moral Lens
Evaluate ethical implications
Assesses content against 13 universal moral principles including dignity, honesty, equality, justice, and freedom.
Scientific Rigour
Separate science from pseudoscience
Detects factual errors, pseudoscience, cherry-picked data, misrepresented evidence, and causal fallacies in scientific claims.
Legal Risk
Check legal soundness
Evaluates whether proposals or claims comply with criminal, civil, constitutional, and international law.
Historical Parallels
Learn from the past
Finds historical precedents for current events. Understand patterns, draw parallels, and learn from how similar situations played out.
Critique
Think deeper about what you read
A comprehensive critical thinking analysis that identifies unsupported claims, missing context, logical flaws, and oversimplifications.
Omissions
Notice what was left out
Surfaces the facts, context, perspectives, and counterpoints a well-informed reader would expect — but the article leaves out.
Background
Get up to speed fast
Builds the context around a topic: what it is, how it developed over time, and where things stand now — orientation for a reader new to the story.
Rewrite
Read it de-spun
The article rewritten neutrally and more briefly. Strictly subtractive: it never adds a fact, so you can check the de-spun, condensed version against the source.
Roast
The fun one
A warm, witty comedian’s take on the article — a punchy verdict and a few standalone jokes about its most roastable details. Pure entertainment.
Every analysis type is included in every plan — even the free trial. BiasChecker is actively developed, so the offering will only get better over time.
All analyses are AI-interpreted patterns and probabilistic observations — not statements of fact, professional advice, or determinations of actual wrongdoing. Results represent one analytical perspective to consider alongside your own judgement. Terms apply.
Choose your plan
Every plan includes every analysis type. Pick the volume that fits how you read. A single analysis checks one article for one type — most people run 3–4 per article.
Plans are measured in analyses. Premium models count as more — a 10× model uses ten analyses' worth — and longer articles cost a little more, since there's more text to read. (Under the hood that's a monthly token allowance, shown on each card; you never have to think in tokens.)
Prices are in USD — you'll be billed in your local currency at checkout.
Trial
Try every analysis type free for 14 days
- All 13 analysis types
- Browser extension
- Any AI model
- Free cached community results
- Credit pack top-ups available
- No credit card required
Lite
Everyday critical reading
- All 13 analysis types
- Browser extension
- Any AI model
- Free cached community results
- Credit pack top-ups available
Pro
PopularFor regular, in-depth readers
- Everything in Lite, plus:
- 2.3× more analyses per month than Lite
*Based on one analysis type per article using 1× basic models (~5,000 tokens per analysis). Most users run 3–4 analysis types per article, giving ~150–200 articles/mo on Lite, ~350–470 on Pro, and ~850–1,130 on Premium. Higher-multiplier models use more tokens per analysis — see the model tiers page. to see estimates based on your own usage.
Subscription plans also include free cached results — if the same article has already been analysed with the same model, you get that result at no cost.
By subscribing, you agree to our Terms of Service and Privacy Policy.
Already analysed? It's free.
Your plan quota is just the starting point. When anyone analyses a web article, that result is cached — so when you open the extension on a page someone has already checked, you get the analysis instantly, at no cost. The more people use BiasChecker, the more of the pages you read are already covered.
So it's not just your monthly analyses — it's that plus anything already analysed on the pages you read. And as we add new analysis types over time, you get them automatically — your plan only gets better.
Don't want to pay monthly?
Buy a credit pack and use it at your own pace — no subscription required. Subscribers top up at a discount too: every pack comes with 25% bonus credits, for the same price.
View credit packs →Frequently Asked Questions
How am I charged?
In tokens — the small chunks of text a model reads and writes. A standard analysis reads the article and writes up its findings, which comes to about 5,000 tokens for an average-length article on a 1× model — that's where “~5,000 tokens per analysis” comes from (a longer article reads more, so it costs more). We scale the actual tokens by the model's tier (1× standard up to 10× frontier) — we call that your “tokens of work” — so a frontier model costs ~10× as many tokens for the same article. The cost comes out of your monthly allowance first, then your credit packs. Cached community results are free on a subscription and during your trial; only pay-as-you-go users are charged for cached ones — a flat one-analysis fee (~5,000 tokens, scaled by the model's tier, so ~5,000 on a 1× model up to ~50,000 on a 10× one), regardless of article length. See the model tiers page for multipliers.
Why “~” analyses, not an exact number?
An analysis's real cost depends on the article's length and the model you choose, so we charge the actual credits used instead of a flat per-analysis fee. A flat fee would either be set low (and lose money on long, premium analyses) or set high (and overcharge you on short ones) — charging real usage is fairer, and a short article on a fast model can cost a small fraction of a heavy one. The analysis counts we quote are honest estimates from typical usage; your credit balance is always exact. Because you only pay for the tokens each analysis actually uses, the same allowance can stretch to more or fewer analyses than the number shown — and the estimate gets more accurate the longer you use BiasChecker, as it learns from your own reading. Sign in and the estimates on these plan cards update to your own usage, so you see an accurate number for how you actually use BiasChecker.
How does the community sharing work?
Every analysis of a web article is shared with the community — except text you paste in directly, which is stored privately under your account (the page URL is never sent), so neither the text nor its results are ever added to the community feed. You don't have to go looking for community analyses, though: turn on Prefer cached results in the extension settings and just analyse pages as usual — when someone has already run that article, BiasChecker loads the existing result instantly instead of running a fresh one. You can tell ahead of time, too: a ✓ next to a model's name in the dropdown means a cached result for that model is ready to load. On subscription plans (Lite, Pro, Premium) — and during your trial — that cached result is free and doesn't count against your monthly analyses; only pay-as-you-go users are charged for cached results. This means the pages you read are often already analysed by the time you open them.
When does my quota reset?
Lite, Pro, and Premium plans reset monthly on your billing date. The trial expires after 14 days.
Can I change plans later?
Yes. Upgrades happen right here and take effect immediately — you're charged a prorated amount for the remainder of your billing period. To downgrade, cancel your current subscription via the customer portal (you keep full access until the end of the period; no refund is issued), then subscribe to the lower tier once it ends.
What is your refund policy?
All purchases — subscriptions and credit packs — are final and non-refundable. You can cancel your subscription at any time to prevent future charges.
Support BiasChecker
BiasChecker is built to make critical thinking accessible to everyone. Every analysis you run benefits the whole community. Here are a few ways you can help us grow.
Get a paid plan
Your subscription keeps the servers running and funds new analysis types. Plus, every article you analyse becomes free to all subscribers — and vice versa.
Spread the word
The bigger the community, the more of the pages you read are already analysed and free to open. Link to BiasChecker from your blog or website, or share on social media.
https://biaschecker.aiGive feedback
Found a bug? Have an idea for a new analysis type? Your feedback directly shapes what we build next.
Rate and review analyses
Let us know when an analysis is spot-on or misses the mark. Your ratings help us improve accuracy for everyone.