The Inference Directory
Explore directory

UberLLM

Verified

UberLLM is listed as a dedicated lab provider with 2 models in the cybersec directory.

Dedicated lab No KYC OpenAI + Anthropic + Responses
Visit provider Compare scores

At a glance

Record
Operator
Not named
Group
Dedicated lab
KYC
No KYC
API shape
OpenAI + Anthropic + Responses
Founded
Not published
Website
uberllm.dev

API access

OpenAI + Anthropic + Responses

Payments

Card

KYC

No KYC

Best score

CyberBench 73.7

Key models

2 listed
DeepSeek V4.1 Flash UncensoredFrontier 1M · 9 uncensored text models taking requests; 3 more listed offline. Abliterated $0.15 / $0.60
Abliterated Large FlashFrontier 1M Abliterated Plan rate / Plan rate

Pricing

List rates · USD per 1M tokens
Model Type Input price Caching price Output price
DeepSeek V4.1 Flash Uncensored1M · 9 uncensored text models taking requests; 3 more listed offline. Frontier $0.15 - $0.60
Abliterated Large Flash1M Frontier Plan rate - Plan rate

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
CryptoNot supported
RailsCard
Minimum top-up$5

Third-party CSV price ($0.0802/$0.8915) disagrees with the provider page ($0.15/$0.60) , verify per model.

KYC

No KYC

No KYC published; card prepaid from $5.

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

Vendor source ↗ · Basis: Directory scan

Scores

Published cyber benchmarks
ModelCyberBenchCyberOffenseCyberGym
DeepSeek V4.1 Flash Uncensored 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.