2026/11/18The November 2026 edition ranks 6 APIs and 8 models
Abliterated API comparison · Updated November 18, 2026

Silk Compute vs Unfil.AI

Silk Compute scores 89.2 to Unfil.AI's 35.4 on the Abliterated API Index, 54 points ahead.

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

Side by side

Silk ComputeUnfil.AI
Index score89.2, #135.4, #4
Blended priceCheapest model with 128K+ context$0.405 · DeepSeek V4.1 Flash 1017$1.20 · Hermes 3 405B
Longest context1M128K
Prompts and outputs storedFrom the privacy policyNeverDeleted within 24 h
1M-context abliterated modelsNamed base models50
Abliterated Kimi K3.1 ProLargest model rankedYesNo
Anthropic Messages endpointNeeded by Claude CodeYesNot stated
OpenAI Responses endpointNeeded by CodexYesNot stated

Shaded cells win the row, as read on November 18, 2026. Unfil.AI review · Silk Compute review

Where Unfil.AI also falls short

  • Usage logs with IP addresses are kept for 30 days.

How to switch

Change the base URL, the key and the model id.

  • hermes-3-llama-3.1-405bkimi-k3.1-pro-uncensored
from openai import OpenAI

client = OpenAI(
    base_url="https://api.silkcompute.com",
    api_key="YOUR_API_KEY",
)
reply = client.chat.completions.create(
    model="kimi-k3.1-pro-uncensored",
    messages=[{"role": "user", "content": "..."}],
)
Try Silk Compute Claude Code setup