Featherless

Verified

Featherless is listed as a dedicated lab provider with 8 models in the cybersec directory.

Dedicated lab No KYC OpenAI-compatible

At a glance

Record
Operator
Featherless AI
Group
Dedicated lab
KYC
No KYC
API shape
OpenAI-compatible
Founded
Not published

Summary

Scope

936 keyword hits in a 22,428-model catalog , duplicates and re-uploads inflate this. Card only.

Says prompts and completions are never stored.

Source: featherless.ai/pricing ↗ · KYC scan 4 November 2026

API access

OpenAI-compatible

Payments

Card

KYC

No KYC

Best score

Coming soon

Key models

8 listed
Llama 3.3 70B Instruct Abliterated 128K Abliterated $0.65 / $0.75
Qwen3.5 27B AbliteratedFrontier 128K Abliterated $0.30 / $2.40
Gemma 4 31B Abliterated v2 256K Abliterated $0.12 / $0.36
Euryale 70B v2.3 128K Abliterated $2.60 / $3.00
Magnum Diamond 70B 128K Abliterated $2.60 / $3.00
DeepSeek R1 Distill Qwen 14B Abliterated 64K Abliterated $0.43 / $1.12
NeuralDaredevil 8B Abliterated 8K Abliterated Plan rate / Plan rate
Llama 3 70B Abliterated v3.5 8K Abliterated Plan rate / Plan rate

Pricing

List rates · USD per 1M tokens
Model Type Input price Caching price Output price
Llama 3.3 70B Instruct Abliterated128K Model $0.65 - $0.75
Qwen3.5 27B Abliterated128K Frontier $0.30 - $2.40
Gemma 4 31B Abliterated v2256K Model $0.12 - $0.36
Euryale 70B v2.3128K Model $2.60 - $3.00
Magnum Diamond 70B128K Model $2.60 - $3.00
DeepSeek R1 Distill Qwen 14B Abliterated64K Model $0.43 - $1.12
NeuralDaredevil 8B Abliterated8K Model Plan rate - Plan rate
Llama 3 70B Abliterated v3.58K Model 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 model

Access

Rails & limits
CardSupported
CryptoNot supported
RailsCard
Minimum top-upNot published

22,428-model catalogue, duplicates inflate keyword counts. Card only means processor checks apply.

KYC

No KYC

No KYC published; card only.

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

Vendor source ↗ · Basis: Directory scan

Scores

Coming soon

Coming soon.

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.