| What it does | Citations, built for AI agents
| Engineering that never sleeps, for every app
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| FR
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free tier for small requests with no API key required; 10 million free tokens to start; $1 per million tokens for pay-as-you-go, with discounts available at volume or with annual commitments; failed requests are never charged.
| Free plan includes 1,000 credits per month. Starter begins at $25/month (10,000 to 50,000 credits, at $2.50 per 1,000 credits). Pro begins at $180/month (80,000 to 320,000 credits, at $2.25 per 1,000 credits). Enterprise pricing is custom. Annual Pro includes two months free and done-for-you migrati
|
|---|
| Key features | - Token-level attribution with confidence scores
- Works with any AI model without access to weights or internals
- Processes documents up to 1 million tokens
- Returns results in under 2 seconds for 20,000-token documents
- On-premise and air-gapped deployment options
- PDF support with character-level mapping
- Supports 23+ languages including Indian languages
- Chrome browser extension for page and PDF tracing
- Raw token-by-token heatmaps available via API
- No data logging or training on request content
| - Pre-launch security, reliability, data, performance, cost, and code quality audit
- 24/7 uptime monitoring with downtime alerts
- Error tracking and session replay with 90 days history
- AI-powered fix prompts that work with Lovable, Bolt, Replit, and Claude Code
- Unlimited apps on any plan with shared credit balance
- Status page and Trust Page for user transparency
- GitHub integration for code change detection
- Slack alerts and webhooks on Pro and above
- Migration done-for-you on annual Pro plan
|
|---|
| What makes it different | - Measures attention directly from the model's computation rather than asking the model to cite itself, providing verifiable attribution
- Achieves frontier-grade citation quality at 7x lower cost and 5-6x faster than alternatives
- Never confused by duplicate facts—identifies the exact occurrence the answer used even when values appear multiple times
- Lands on exact tokens down to character level, not just document chunks
- Works on any model's output post-generation without modifying inference pipeline
| - Works with every AI builder, not just one—covers Lovable, Bolt, Replit, Base44, Claude Code, and others
- Monitoring and watching never consume credits—only work is metered
- Plain-language findings and fix prompts for non-engineers
- Your code and accounts stay yours—read-only audit and month-to-month plans
- Open source browser SDK published under MIT License
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 2 ● no change since last check | 4 ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 4 |
|---|
| Citation Flow (Majestic) | 16 | 23 |
|---|
| Referring domains (Majestic) | 36 | 12 |
|---|
TokenPath
BWorlds