The Inference Directory
Explore directory

Refuseless

Verified

Refuseless is listed as a dedicated lab provider with 5 models in the cybersec directory.

Dedicated lab No KYC OpenAI-compatible
Visit provider Compare scores

At a glance

Record
Operator
Refuseless (US)
Group
Dedicated lab
KYC
No KYC
API shape
OpenAI-compatible
Founded
2026

Summary

Scope

New (Oct 2026). Some non-ZR models can spill to anonymized partner routes.

Zero prompt retention; in-memory only. Billing keeps token counts and cost.

Source: refuseless.com/pricing ↗ · KYC scan 4 November 2026

API access

OpenAI-compatible

Payments

CardBitcoinEthereumUSDTUSDCMonero

KYC

No KYC

Best score

CyberBench 72.1

Key models

5 listed
GLM 5.3 AbliteratedFrontier 1M · 38% off list; 85 tok/s. Abliterated $1.25 / $2.25
GLM 5.3 Flash AbliteratedFrontier 1M · 47% off list; 130 tok/s. Abliterated $0.15 / $0.50
DeepSeek V4.1 Flash 1017 AbliteratedFrontier 1M · 55% off list; 400 tok/s. Abliterated $0.22 / $0.75
DeepSeek V4.1 Flash 1017 (stock)Frontier 1M · Not abliterated. · Stock Stock $0.05 / $0.15
MiniMax M3.1 Flash 1M · Not abliterated. · Stock Stock $0.05 / $0.25

Pricing

List rates · USD per 1M tokens
Model Type Input price Caching price Output price
GLM 5.3 Abliterated1M · 38% off list; 85 tok/s. Frontier $1.25 - $2.25
GLM 5.3 Flash Abliterated1M · 47% off list; 130 tok/s. Frontier $0.15 - $0.50
DeepSeek V4.1 Flash 1017 Abliterated1M · 55% off list; 400 tok/s. Frontier $0.22 - $0.75
DeepSeek V4.1 Flash 1017 (stock)1M · Not abliterated. Frontier $0.05 - $0.15
MiniMax M3.1 Flash1M · Not abliterated. Stock $0.05 - $0.25

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, Ethereum, USDT, USDC, Monero
Minimum top-upNot published

Visa/Mastercard + 5 coins. Crypto payments non-refundable; card refundable if <5% used.

KYC

No KYC

No KYC/ID requirement published. Sign up with email or Google.

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

Vendor source ↗ · Basis: Vendor statement

Scores

Published cyber benchmarks
ModelCyberBenchCyberOffenseCyberGym
GLM 5.3 Abliterated 72.1 - 84.5
GLM 5.3 Flash Abliterated 67.9 19.2 -
DeepSeek V4.1 Flash 1017 Abliterated 73.7 72.8 88.1

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.