The Inference Directory
Explore directory

MagmaRouter

Verified

MagmaRouter is listed as a dedicated lab provider with 6 models in the cybersec directory.

Dedicated lab No KYC OpenAI + Anthropic
Visit provider Compare scores

At a glance

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

Summary

Scope

Only 6 models. Payment rails thin; no card support documented.

No prompt/completion stored; 90-day metadata; signed prompt-hash receipts.

Source: magmarouter.com/models/ ↗ · KYC scan 4 November 2026

API access

OpenAI + Anthropic

Payments

Crypto

KYC

No KYC

Best score

CyberBench 72.1

Key models

6 listed
GLM 5.3 XplodedFrontier 1.05M Abliterated $2.00 / $5.00
GLM 5.3 Flash XplodedFrontier 1.05M Abliterated $0.30 / $1.00
DeepSeek V4.1 Flash 1017 XplodedFrontier 1.05M Abliterated $1.00 / $2.50
MiMo V2.6 Flash XplodedFrontier 1.05M Abliterated $1.00 / $2.00
Qwen3.8 27B XplodedFrontier 1.05M Abliterated $1.50 / $5.00
Qwen3.8 27B Ultrafast XplodedFrontier 524K Abliterated $1.75 / $5.50

Pricing

List rates · USD per 1M tokens
Model Type Input price Caching price Output price
GLM 5.3 Xploded1.05M Frontier $2.00 - $5.00
GLM 5.3 Flash Xploded1.05M Frontier $0.30 - $1.00
DeepSeek V4.1 Flash 1017 Xploded1.05M Frontier $1.00 - $2.50
MiMo V2.6 Flash Xploded1.05M Frontier $1.00 - $2.00
Qwen3.8 27B Xploded1.05M Frontier $1.50 - $5.00
Qwen3.8 27B Ultrafast Xploded524K Frontier $1.75 - $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
RailsCrypto
Minimum top-up$5 min + 3.15% + $0.30

Crypto-only checkout. 6 Xploded models only. Claims zero retention.

KYC

No KYC

No KYC. No card payments , crypto on-chain only.

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

Vendor source ↗ · Basis: Directory scan

Scores

Published cyber benchmarks
ModelCyberBenchCyberOffenseCyberGym
GLM 5.3 Xploded 72.1 - 84.5
GLM 5.3 Flash Xploded 67.9 19.2 -
DeepSeek V4.1 Flash 1017 Xploded 73.7 72.8 88.1
MiMo V2.6 Flash Xploded 75.4 - -
Qwen3.8 27B Xploded 67.8 - -
Qwen3.8 27B Ultrafast Xploded 67.8 - -

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.