The Inference Directory
Explore directory

AnonRouter

Verified

AnonRouter is listed as a router provider with 4 models in the cybersec directory.

Router No KYC OpenAI-compatible
Visit provider Compare scores

At a glance

Record
Operator
AnonRouter
Group
Router
KYC
No KYC
API shape
OpenAI-compatible
Founded
Not published

Summary

Scope

Crypto is not automatically anonymous (public chain). E2EE only where upstream supports it.

No prompt/response storage; attested Intel TDX routing plane.

Source: anonrouter.ai/pricing ↗ · KYC scan 4 November 2026

API access

OpenAI-compatible

Payments

CardBitcoinLightning

KYC

No KYC

Best score

Coming soon

Key models

4 listed
GLM 4.7 Flash Heretic 200K · Private route. Abliterated $0.07 / $0.40
Venice Uncensored 1.2 128K · Private route. Abliterated $0.20 / $0.90
Gemma 4 26B A4B Uncensored 64K · E2EE route. Abliterated $0.19 / $0.88
Venice Role Play Uncensored 128K · Private route. Abliterated $0.50 / $2.00

Pricing

List rates · USD per 1M tokens
Model Type Input price Caching price Output price
GLM 4.7 Flash Heretic200K · Private route. Model $0.07 - $0.40
Venice Uncensored 1.2128K · Private route. Model $0.20 - $0.90
Gemma 4 26B A4B Uncensored64K · E2EE route. Model $0.19 - $0.88
Venice Role Play Uncensored128K · Private route. Model $0.50 - $2.00

List rates. Cached input shown where published; "-" means the provider does not publish a cache rate. Workload comparison uses 1M input plus 250K output. Per 1M tokens

Access

Rails & limits
CardSupported
CryptoSupported
RailsCard, Bitcoin, Lightning
Minimum top-up$5 (5% fee, $0.75 min)

Card payments still pass the processor's identity checks. Crypto is not automatically anonymous (public chain).

KYC

No KYC

"A private account does not require an email address." No ID/KYC process published.

No ID step at signup or checkout; email + card/crypto only

Vendor source ↗ · Basis: Vendor statement

Scores

Coming soon

Coming soon.

Performance

Coming soon
Latency

Time to first token

Median and p95 response times for short and long prompts, measured from repeatable probes rather than vendor claims.

Coming soon
Throughput

Tokens per second

Streaming output rate and request throughput under steady load, with concurrency and context length recorded.

Coming soon
Efficiency

Cost per workload

Blended cost for a fixed workload, including cache reads and output tokens, so speed and price can be compared together.

Coming soon

Independent performance probes are being added. Vendor-reported numbers are not mixed into this section.