The Inference Directory
Explore directory

Dagon Inference

Verified

Dagon Inference is listed as a router provider with 2 models in the cybersec directory.

Router No KYC OpenAI + Anthropic
Visit provider Compare scores

At a glance

Record
Operator
Not named
Group
Router
KYC
No KYC
API shape
OpenAI + Anthropic
Founded
Not published

Summary

Scope

15% lease markup; $10 lease cap. Upstream retention claims unverifiable. Front-end for Abliteration, Refuseless, Experiential.

Prompts pass through memory, not DB/logs; gateway sees IP + timing. Signed receipts.

Source: inference.dagon.so/ ↗ · KYC scan 4 November 2026

API access

OpenAI + Anthropic

Payments

USDC

KYC

No KYC

Best score

CyberBench 73.7

Key models

2 listed
Abliterated Large FlashFrontier 1M · Cheapest healthy upstream +10%. Abliterated $1.00 / $2.20
Abliterated Large V2Frontier 1M · Estimated +10% on $3/$5. Abliterated $3.30 / $5.50

Pricing

List rates · USD per 1M tokens
Model Type Input price Caching price Output price
Abliterated Large Flash1M · Cheapest healthy upstream +10%. Frontier $1.00 $0.11 $2.20
Abliterated Large V21M · Estimated +10% on $3/$5. Frontier $3.30 $0.17 $5.50

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
CardNot supported
CryptoSupported
RailsUSDC
Minimum top-up$5

Gateway in front of Abliteration.ai, Refuseless and Experiential Labs; +10% (+15% on leases). Key is unrecoverable (hash only).

KYC

No KYC

"No email, no account form" , key issued at checkout, paid in USDC.

Vendor states it does not ask for KYC/ID

Vendor source ↗ · Basis: Vendor statement

Scores

Published cyber benchmarks
ModelCyberBenchCyberOffenseCyberGym
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.