Method

DeepSeek V4.1 Flash 1017 unrestricted: refusals, size and price

Available on
Silk ComputeMorphAbliteration
Size#2 / 9
Rank among the 9 models here
763BTotal parameters
Context#1 / 9
Max output 131,072
1M1,048,576 tokens
Priceper 1M tokens
In $0.24Out $0.90Cached $0.038
$0.41Blended price at Silk Compute
Inputs#2 / 9
text, images
2Input types

DeepSeek V4.1 Flash 1017 has the lowest blended price of the hosted models here. It reads text and images with a 1,048,576-token context.

The refusal direction is found in the activations and projected out of the weights.

Technical specifications

Refusals removed by
Abliterated
Model maker
DeepSeek
Parameters
763B
Context window
1,048,576
Max output
131,072
Inputs
Weights
Open weights
Tool calling
Yes
Reasoning effort
Low, high, max
API id
deepseek-v4.1-flash-1017-uncensored

Where to run it

Prices per 1M tokens, read November 18, 2026.

HostModel idInputper 1MOutputper 1MContextAPI formatsAccess
Silk Computedeepseek-v4.1-flash-1017-uncensored$0.24$0.901,048,576Chat Completions, Messages, ResponsesSign up with a verified emailVisit
Silk Compute (Fast id)deepseek-v4.1-flash-1017-fast-uncensored$0.24$0.901,048,576Chat Completions, Messages, ResponsesSign up with a verified emailVisit
Morphmorph-dsv41flash-uncensored$0.30$1.201MChat Completions, Messages, ResponsesApproval requiredVisit
Abliterationabliterated-model-large-flash$1.00$2.001,048,576Chat Completions, Messages, ResponsesSign upVisit

Call it

Any OpenAI-compatible client works with the base URL https://api.silkcompute.com.

curl https://api.silkcompute.com/chat/completions \
  -H "Authorization: Bearer $SILK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek-v4.1-flash-1017-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'

Guides: quickstart, Claude Code, Codex, OpenCode.

Against the other models

Size

Total parameters, billions. Log scale. Larger is more capable

2,780 Kimi K3.1 Pro 763 DeepSeek V4.1 Flash 753 GLM-5.3 405 Hermes 3 405B 320 GLM-5.3 Flash 36 Qwen 3.6 35B 31.3 Gemma 4 31B 27.8 Qwen 3.8 27B 8 Llama 3.1 8B

Context window

Tokens the model holds at once. Higher is better

1M Kimi K3.1 Pro 1M DeepSeek V4.1 Flash 1M GLM-5.3 1M GLM-5.3 Flash 256K Qwen 3.6 35B 256K Gemma 4 31B 256K Qwen 3.8 27B 128K Hermes 3 405B 128K Llama 3.1 8B

Price

Blended USD per 1M tokens, lowest listed host. Lower is better

$0.41 DeepSeek V4.1 Flash $0.43 GLM-5.3 Flash $1.20 Hermes 3 405B $2.50 GLM-5.3 $4.20 Qwen 3.8 27B $4.63 Kimi K3.1 Pro
AbliteratedFine-tunedHatched: weights only, no API listed

Compare