# PPQ.ai | Abliterated AI inference profile and prices

[Directories](/directories/) › [Cybersec & Abliterated](/cybersec/) › PPQ.ai

![PPQ.ai logo](/logos/ppq.png)

Verified

PPQ.ai is listed as a router provider with 8 models in the cybersec directory.

Router No KYC OpenAI-compatible

[Visit provider ↗](https://ppq.ai) [Compare scores →](/cybersec/compare/)

Overview Models Pricing Access KYC Scores Performance

## At a glance

Record

Operator

PayPerQ

Group

Router

KYC

No KYC

API shape

OpenAI-compatible

Founded

Not published

Website

[ppq.ai](https://ppq.ai)

## Summary

Scope

Card payments link the card to a credit id at Stripe. ~5.5% over upstream.

Chat runs in an AWS Nitro enclave; PPQ says it cannot read prompts. Billing metadata kept per request.

[Source: ppq.ai/llms.txt ↗](https://ppq.ai/llms.txt) · KYC scan 4 November 2026

### API access

OpenAI-compatible

### Payments

CardBitcoinLightningLitecoinMoneroL402

### KYC

No KYC

### Best score

CyberBench 73.7

## Key models

8 listed

Venice Uncensored 1.2 128K Abliterated $0.21 / $0.95

Venice Role Play Uncensored 128K Abliterated $0.53 / $2.11

GLM 4.7 Flash Heretic 200K Abliterated $0.07 / $0.42

Gemma 4 Uncensored 256K Abliterated $0.17 / $0.53

DeepSeek V4.1 Flash UncensoredFrontier 1M Abliterated $0.35 / $1.39

Abliterated Large FlashFrontier 1M Abliterated $1.32 / $2.64

Abliterated Large V2Frontier 1M Abliterated $3.17 / $5.28

Gemma 4 26B A4B Uncensored (E2EE) 64K Abliterated $0.20 / $0.93

## Pricing

List rates · USD per 1M tokens

Model Type Input price Caching price Output price

Venice Uncensored 1.2128K Model $0.21 \- $0.95

Venice Role Play Uncensored128K Model $0.53 \- $2.11

GLM 4.7 Flash Heretic200K Model $0.07 $0.037 $0.42

Gemma 4 Uncensored256K Model $0.17 \- $0.53

DeepSeek V4.1 Flash Uncensored1M Frontier $0.35 $0.0087 $1.39

Abliterated Large Flash1M Frontier $1.32 $0.13 $2.64

Abliterated Large V21M Frontier $3.17 $0.32 $5.28

Gemma 4 26B A4B Uncensored (E2EE)64K Model $0.20 \- $0.93

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

Card**Supported**

Crypto**Supported**

Rails**Card, Bitcoin, Lightning, Litecoin, Monero, L402**

Minimum top-up**Lightning $0.10 · LTC/Liquid $2 · XMR $5 · on-chain BTC $10**

Caveat: stablecoin deposits routed via MixPay can be AML-screened and MixPay may demand KYC. Self-operated BTC/LTC/DOGE/XMR deposits have no third-party processor.

## KYC

No KYC

No KYC described anywhere; account is optional and only an email is collected if you create one. L402 pay-per-request needs no account or API key.

Vendor states it does not ask for KYC/ID

[Vendor source ↗](https://ppq.ai/api-docs) · Basis: Vendor statement

## Scores

Published cyber benchmarks

ModelCyberBenchCyberOffenseCyberGym

DeepSeek V4.1 Flash Uncensored 73.7 72.8 88.1

Abliterated Large Flash 73.7 \- \-

Abliterated Large V2 72.1 \- 84.5

## 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.

[PreviousMorpheus](/cybersec/providers/morpheus) [NextVenice.ai](/cybersec/providers/venice)