Method

Kimi K3.1 Pro unrestricted: refusals, size and price

Available on
Silk Compute
Size#1 / 9
Rank among the 9 models here
2,780BTotal parameters
Context#1 / 9
Max output 943,718
1M1,048,576 tokens
Priceper 1M tokens
In $3.50Out $8.00Cached $0.35
$4.63Blended price at Silk Compute
Inputs#1 / 9
text, images, video
3Input types

Kimi K3.1 Pro is the largest unrestricted model here and the only one that reads video. It is the first pick for security research, red teaming and long agentic coding runs.

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

Technical specifications

Refusals removed by
Abliterated
Model maker
Moonshot AI
Parameters
2,780B
Context window
1,048,576
Max output
943,718
Inputs
Weights
Open weights
Tool calling
Yes
Reasoning effort
Low, high, max
API id
kimi-k3.1-pro-uncensored

Where to run it

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

HostModel idInputper 1MOutputper 1MContextAPI formatsAccess
Silk Computekimi-k3.1-pro-uncensored$3.50$8.001,048,576Chat Completions, Messages, ResponsesSign up with a verified emailVisit

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": "kimi-k3.1-pro-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'

Guides: quickstart, Claude Code, Codex, OpenCode, security research setup, red teaming setup.

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