2026/11/18The November 2026 edition ranks 6 APIs and 8 models
DeepSeek

DeepSeek V4.1 Flash 1017 Abliterated

DeepSeek V4.1 Flash 1017 Abliterated is DeepSeek's 763B October checkpoint with its refusal direction removed, and the best-value model in this ranking.

Rank#2 / 8
#2Editors' ranking
Size#2 / 8
763BTotal parameters
Price#1 / 5
$0.405Blended per 1M, lowest host
Context
1MTokens per request

Our pick for coding agents and all-day use.

Input
Price in / out$0.24 / $0.90
Context1M tokens
Max output131,072
ReleasedOctober 2026
Model iddeepseek-v4.1-flash-1017-uncensored

Its low price counts most in agent runs, which resend the whole context every turn.

Silk Compute serves it with low, high and max reasoning effort, so triage can run on low and a hard bug on max.

Where to run DeepSeek V4.1 Flash by API

Blended price per 1M tokens, 3 input to 1 output.

Silk Compute$0.405Morph$0.525abliteration.ai$1.25
ProviderModel idInputCachedOutputContextPrompts
Silk Computedeepseek-v4.1-flash-1017-uncensored$0.24$0.038$0.901MNever stored
MorphApproval requiredmorph-dsv41flash-uncensored$0.30$0.03$1.201MUp to 30 days
abliteration.aiabliterated-model-large-flash$1.00$0.10$2.001MNever stored

Per 1M tokens, read from pricing pages on November 18, 2026.

Try DeepSeek V4.1 Flash in two lines

Set the base URL and your key in the OpenAI or Anthropic SDK.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.silkcompute.com",
    api_key="YOUR_API_KEY",
)
reply = client.chat.completions.create(
    model="deepseek-v4.1-flash-1017-uncensored",
    messages=[{"role": "user", "content": "..."}],
)

In Claude Code:

export ANTHROPIC_BASE_URL=https://api.silkcompute.com
export ANTHROPIC_AUTH_TOKEN=YOUR_API_KEY
export ANTHROPIC_MODEL=deepseek-v4.1-flash-1017-uncensored
claude
DeepSeek V4.1 Flash on Silk Compute

Compared with

Ranked for

Other abliterated models