Silk Compute vs Featherless

Silk Compute serves four large uncensored models with a 1,048,576-token context; Featherless serves abliterated community models up to 72B with a 32K context. Silk Compute also serves the Messages and Responses formats that Claude Code and Codex need.

Updated Prices read November 18, 2026

uncensoredllmprovider.com is published by the team behind Silk Compute, one of the providers ranked here.

Silk Compute
Featherless

Overview

Grid models served4 of 4
Grid models served0 of 4
Largest uncensored modelKimi K3.1 Pro 2,780B
Largest uncensored modelQwen2.5 72B Abliterated 72B
Context window1,048,576
Context window32,768
Input typesText, images, video
Input typesText, images

Pricing

Lowest plan for API use$10 a month
Lowest plan for API use$50 a month
Max output, largest model943,718
Max output, largest model32,768

Data

Data policyZero data retention
Data policyNot logged

API formats

Chat CompletionsYes
Chat CompletionsYes
Anthropic MessagesYes
Anthropic MessagesNot stated
OpenAI ResponsesYes
OpenAI ResponsesNot stated

Payment

CardYes
CardYes
CryptoMonero, Bitcoin, Ether, USDT, USDC
CryptoNone listed

Switch from Featherless

Point an OpenAI SDK client at Silk Compute's base URL and pick a model id; the quickstart covers keys.

Python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.silkcompute.com",
    api_key=os.environ["SILK_API_KEY"],
)

reply = client.chat.completions.create(
    model="deepseek-v4.1-flash-1017-uncensored",
    messages=[{"role": "user", "content": "Hello"}],
)

Related