AI Text Detector
Detect text written by GPT-5.5, GPT-5.5 Pro, Claude Opus 4.7, Claude Sonnet 4.6 and Gemini 3.1 Pro. Per-sentence highlights and model attribution. 99.1% accuracy on the RAID benchmark. $1 in free scan credit on signup. Lifetime scan history on every plan.
How it works
Paste, scan, verify - in under two seconds.
Paste text
Drop in any text - essay, article, email, chat. No upload needed for short copy under 5,000 characters.
Cross-model analysis
Tokenisation, perplexity, burstiness and a learned classifier run in parallel. Median verdict in 1.6 seconds.
Per-sentence verdict
Get the AI score, confidence band, model attribution (GPT-5.5 vs Claude vs Gemini) and per-sentence highlights.
What the ai text detector actually catches.
Six headline generators, sampled across every modality we cover. Each entry is benchmarked monthly against the vendor's latest release - we cycle the roster instead of padding it.
- 01/06TextOpenAIGPT-5.5release 5.5ActiveRAID benchmark
- 02/06TextOpenAIGPT-5.5 Prorelease 5.5 ProActiveLong-form essays
- 03/06TextOpenAIGPT-5.4release 5.4ActiveLegacy fallback
- 04/06TextAnthropicClaude Opus 4.7release Opus 4.7ActiveSentence-level
- 05/06TextAnthropicClaude Sonnet 4.6release Sonnet 4.6ActiveSentence-level
- 06/06TextGoogleGemini 3.1 Prorelease 3.1 ProActiveCross-lingual
Accuracy & methodology
Benchmark first. Hype never.
We benchmark at 99.1% accuracy on the RAID benchmark across GPT-5.5, GPT-5.5 Pro and Claude Opus 4.7 outputs, with a 1.2% false-positive rate. The detection methodology is a cross-model ensemble combining tokenisation patterns, perplexity, burstiness and a learned classifier. Confidence bands are surfaced on every result so you can decide what to do with the verdict.
Use cases
Who uses it.
Educators
Detect AI-written essays before grading. Per-sentence highlights show exactly which lines came from a model.
Publishers & editors
Verify freelance submissions and PR pitches at scale. Bulk upload supports 50 files per scan on Pro.
Recruiters
Check candidate take-homes and cover letters for authenticity without false-flagging legitimate writers.
SEO & content teams
Audit your own pipeline. Catch low-effort AI drafts before they ship to the CMS.
Comparison
How does this compare to other detectors?
We're honest about competitor strengths. Most are text-only; ai-detectors.io is the multi-modal alternative with $1 in free credit instead of a $14.95 paid minimum.
Pricing
One credit pool. Four plans.
Lifetime scan history on every plan. Same accuracy across every model. No retention tier, no per-modality caps to juggle.
Save 50% paying yearly. Upgrade or cancel any time.
Free
Try itFree forever, no card required
Try every text and image model. $1 in credit on signup.
Credit
- $1 in signup credit
- No top-ups
Modalities
Limits
- 25,000 chars / scan
- 5 MB per image
Features
- Per-sentence highlights
- Model attribution
- API access
Support
- Community
- Lifetime scan history
Starter
SoloBilled yearly - $54/year
Sentence-level highlights and bulk text scans for solo writers.
Credit
- $12 credit / month
- Top-up packs available
Modalities
Limits
- 75,000 chars / scan
- 10 MB per image
Features
- Per-sentence highlights
- Model attribution
- API access
Support
- Email · 72h
- Lifetime scan history
Pro
Multi-modalBilled yearly - $114/year
All four modalities with model attribution.
Credit
- $25 credit / month
- Top-up packs available
Modalities
Limits
- 150,000 chars / scan
- 25 MB per image
- 10 min per audio
- 5 min per video
Features
- Per-sentence highlights
- Model attribution
- API access
Support
- Email · 24h
- Lifetime scan history
Business
ScaleBilled yearly - $294/year
API access and bulk pipelines for teams at scale.
Credit
- $75 credit / month
- Top-up packs available
Modalities
Limits
- 150,000 chars / scan
- 50 MB per image
- 60 min per audio
- 30 min per video
Features
- Per-sentence highlights
- Model attribution
- API access
Support
- Priority · 4h
- Lifetime scan history
One-time top-ups
Top up any time. Bigger pack, bigger bonus.
Buy more credit without changing plans. Same balance, every modality.
| Compare plans | Free | Starter | Pro | Business |
|---|---|---|---|---|
| Monthly | $0 | $9 | $19 | $49 |
| Annual (-50%) | - | $4.50 | $9.50 | $24.50 |
| Credit | $1 (signup) | $12/mo | $25/mo | $75/mo |
| Top-up | ||||
| Text | ||||
| Image | ||||
| Audio | ||||
| Video | ||||
| Characters / scan | 25,000 | 75,000 | 150,000 | 150,000 |
| Image size | 5 MB | 10 MB | 25 MB | 50 MB |
| Audio length | - | - | 10 min | 60 min |
| Video length | - | - | 5 min | 30 min |
| Scan history | Forever | Forever | Forever | Forever |
| Per-sentence highlights | ||||
| Model attribution | ||||
| API access | ||||
| Support | Community | Email · 72h | Email · 24h | Priority · 4h |
FAQ
Common questions about the ai text detector.
The ai text detector is tuned against GPT-5.5, GPT-5.5 Pro, GPT-5.4, Claude Opus 4.7, Claude Sonnet 4.6, Gemini 3.1 Pro and Gemini 3 Flash. New models are added to the ensemble within 30 days of release.
We benchmark at 99.1% accuracy on the RAID benchmark with a 1.2% false-positive rate for text, and 96.9-98.4% across image, audio and video. Every verdict ships with a confidence band so you know how certain the result is.
Edited prose, technical writing and ESL writing are common false-positive triggers for naive detectors. We tune against those failure modes specifically and surface confidence so a low-certainty AI verdict reads differently from a high-certainty one.
Yes. Every plan keeps every scan forever - Free included. There is no retention tier and never will be. You can delete an individual scan from /dashboard/history at any time.
No. Uploads are processed in-memory and never used to train detectors. We are SOC 2 in progress and ship a Data Processing Addendum.
Every signup gets $1 in scan credit, usable across every detector model - text, image, audio, video. There is no expiry while your account is active.
Yes - Starter handles 10 files at once, Pro 50 and Business 500. Drop a folder into the dashboard and we'll scan everything in parallel.
Yes - included on the Business plan. The API mirrors the dashboard, supports streaming results for long videos and ships an OpenAPI spec.
We don't sell humanisers, evasion or AI-paraphrasing. We're a verdict tool. If you want to bypass detection, this isn't the product for you.
Detector library
Other detectors you might need
Detection is multi-modal. The same scan and the same credit pool work across every tool.
Get $1 free credit - start scanning.
Lifetime scan history. Every plan. No retention tier.