Silk Compute

Verified

Silk Compute is listed as a dedicated lab provider with 4 models in the cybersec directory.

Dedicated lab No KYC OpenAI-compatible

At a glance

Record
Operator
Silk Compute
Group
Dedicated lab
KYC
No KYC
API shape
OpenAI-compatible
Founded
Not published

Summary

Scope

Uncensored frontier models only. Every model has a 1M context. Kimi K3.1 is listed as coming soon.

Prompts and completions are not stored. Technical logs age out. Stripe handles cards; CryptAPI handles non-Monero crypto.

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

API access

OpenAI-compatible

Payments

CardMoneroBitcoinEthereumUSDTUSDC

KYC

No KYC

Best score

CyberBench 73.7

Key models

4 listed
Kimi K3.1 UncensoredFrontier 1M · Coming soon Abliterated $2.00 / $10.00
DeepSeek V4.1 Flash 1017 UncensoredFrontier 1M Abliterated $0.28 / $1.00
GLM-5.3 UncensoredFrontier 1M · Best at cyber Abliterated $2.00 / $4.00
GLM-5.3 Flash UncensoredFrontier 1M Abliterated $0.24 / $1.00

Pricing

List rates · USD per 1M tokens
Model Type Input price Caching price Output price
Kimi K3.1 Uncensored1M · Coming soon Frontier $2.00 $0.2 $10.00
DeepSeek V4.1 Flash 1017 Uncensored1M Frontier $0.28 $0.07 $1.00
GLM-5.3 Uncensored1M · Best at cyber Frontier $2.00 $0.3 $4.00
GLM-5.3 Flash Uncensored1M Frontier $0.24 $0.08 $1.00

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. Cached input from $0.07.

Access

Rails & limits
CardSupported
CryptoSupported
RailsCard, Monero, Bitcoin, Ethereum, USDT, USDC
Minimum top-upPay-as-you-go credits from $5. Plans from $9/month billed yearly.

Uncensored frontier models only. Every model has a 1M context. Verify the checkout rate before buying.

KYC

No KYC

Cards through Stripe, and crypto: Monero, Bitcoin, Ether, and USDT or USDC stablecoins. No KYC/ID process published.

No ID step at signup or checkout; account + Stripe card or crypto

Vendor source ↗ · Basis: Vendor statement

Scores

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

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.