Number 1: 
Ora
Make your site work for agents
- AI testing & review
- United States
- DR 60 +1 (up) since last check
AI testing & review
TokenPath
Citations, built for AI agents
- Community votes
- 0
- DR by Ahrefs
- 2 no change since last check
Ahrefs Domain Rating benchmarked 1 Nov 2026, rebuilt 1 Nov 2026.
An API that grounds every generated token in its source by measuring attention directly, returning machine-readable token-level citations for output from any
What it is
TokenPath is an API that traces AI-generated answers back to their exact sources by measuring attention directly from the model's computation. You send a document, question, and answer; the API returns which spans of the answer came from which spans of the document with confidence scores. It works with any model including GPT, Claude, Gemini, and Llama, requires no access to model weights or internals, and can run on-premise in your own VPC. TokenPath achieves frontier-grade citation quality without the frontier cost, scoring 0.815 F1 on LongBench-Cite while being approximately 7 times cheaper and 5-6 times faster than comparable solutions.
What it is built with
- 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
Pricing
Pricing model: Freemium
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.
TokenPath metrics
| Metric | Value |
|---|---|
| Domain Rating | 2 no change since last check |
| Trust Flow | 3 no change since last check |
| Citation Flow | 16 no change since last check |
| Referring domains | 36 no change since last check |
| External backlinks | 125 no change since last check |
Ahrefs Domain Rating benchmarked 1 Nov 2026, rebuilt 1 Nov 2026. Main build topic: Computers/Computer Science/Academic Departments (3). Majestic benchmarked 1 Nov 2026, rebuilt 1 Nov 2026. Link data built by Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.
TokenPath domain build sheet
Open the build sheet
| Domain age | 8 months |
|---|---|
| Registered | |
| Expires | |
| Registrar | GoDaddy.com, LLC |
| DNSSEC | Not signed |
TokenPath after-launch build log
Since TokenPath launched on Maker Launches on 1 November 2026, these are the figures we have tracked.
- Domain Rating (Ahrefs)
- 2
- First measured 1 Nov 2026
- Referring domains (Majestic)
- 36
- First measured 1 Nov 2026
Day 0 since launch. Next receipt: day 30, 1 Dec 2026. We show what changed, not what caused it: many things affect these numbers. Nothing here is estimated.
Compare and explore
Questions from the bench
- What exactly is the TokenPath API?
- One HTTP endpoint where you send a document, question, and answer already produced by your model. You get back which spans of the answer came from which spans of the document with confidence scores. TokenPath generates nothing, rewrites no prompts, and operates after the answer exists as a pure measurement.
- Does it work with my model?
- Yes, all of them. Attribution runs after generation and needs only text, not access to model weights, logprobs, or internals. GPT, Claude, Gemini, Llama, custom fine-tunes, or final answers from multi-step agents all work identically by reading the attention of TokenPath's attribution model over your document and answer.
- Can we run TokenPath on-premise, or in our own VPC?
- Yes. Attribution runs on open-weight models on GPUs operated by TokenPath with no OpenAI, Anthropic, or Google in the path, and nothing that phones home. The entire system can run inside your network air-gapped if required, though it is not self-serve and requires discussion with sales to size properly.
- What does it cost?
- Small requests are free with no API key. Beyond that, $1 per million tokens pay-as-you-go, counted across document, question, and answer. This is the on-demand list price, with substantial discounts available at volume or with annual commitments. Start with 10 million free tokens and no card required.
- How fast is it, and how long can the document be?
- A 20,000-token document (roughly 30 pages) returns in under two seconds. Longer source text up to 1 million tokens is automatically split into overlapping model-sized windows, with a result returned only once every window succeeds.
Leave a review for TokenPath
Nobody has put TokenPath on the bench yet. Leave the first review.
Reviewing is free, and nobody can pay for a review. Read the bench notes
Maker reviews · Workshop notes · Show it off · Did you make this? Claim it · Report this build
TokenPath has a free listing. The owner can unlock the full profile with a paid launch for $5:
- Founder story (locked)
- Milestones (locked)
- Demo video (locked)
- Dofollow website link (locked)
More builds like this
Number 1:
Number 2:
Ocular AIEncoding Human Expertise into Machines
- AI testing & review
- United States
- DR 27 −1 (down) since last check
Number 3:
BWorldsEngineering that never sleeps, for every app
- AI testing & review
- France
- DR 4 no change since last check
Number 4:
OnlineNexusFree accessibility scan and technical fixes for Shopify and WooCommerce stores
- AI testing & review
- Ireland
- DR 0 no change since last check