Silk Compute
Moonshot AIFlagshipNew

Kimi K3.1 Uncensored

kimi-k3.1-uncensored

Kimi K3.1 is Moonshot AI's open-weight model for agentic coding, research and long outputs. This abliterated version has its refusal behavior removed, so it keeps working through long agent loops instead of stopping to decline. It reads up to 1M tokens of context and can write up to 944K tokens in one reply.

Context
1M
Max output
944K
Input
$2.00 / M
Cached input
$0.20 / M
Output
$10.00 / M

Quickstart

Paste the agent prompt into Claude Code, Codex or any coding agent and it sets everything up. Or use the code directly, with SILK_API_KEY set in your shell.

Set up this project to use the Silk Compute API with the model kimi-k3.1-uncensored.

Silk Compute is OpenAI compatible:
- Base URL: https://api.silkcompute.com
- Chat: POST /chat/completions (the Anthropic format is also served at /v1/messages)
- Auth: read the API key from the SILK_API_KEY environment variable. Never hard-code or commit it.

Model kimi-k3.1-uncensored: 1,048,576 tokens of context, up to 943,718 output tokens. Tool calling and streaming are supported.

1. Use the OpenAI SDK if this project already has it; otherwise add the official one for its language.
2. Add a small client that sends a chat request to kimi-k3.1-uncensored and returns the reply text.
3. Add SILK_API_KEY to the example env file if there is one, then show me how to send one test request.

Full API reference: https://silkcompute.com/llms.txt

Questions

Is Kimi K3.1 Uncensored really uncensored?

Yes. It is an abliterated version of Kimi K3.1: the behavior that makes the model refuse has been removed from its weights, and Silk Compute adds no content filter on top. It answers the request instead of declining it.

How much does Kimi K3.1 Uncensored cost?

$2.00 per 1M input tokens, $0.20 per 1M cached input tokens, and $10.00 per 1M output tokens, paid from prepaid credits. There is no subscription, and top-ups start at $5.

How do I use Kimi K3.1 Uncensored in Claude Code, Codex or OpenCode?

Point the tool at https://api.silkcompute.com with your Silk Compute API key and set the model to kimi-k3.1-uncensored. The setup for each tool is on this page and in the docs.

What is the context window of Kimi K3.1 Uncensored?

1,048,576 tokens of context, and up to 943,718 output tokens in one reply.

Does Silk Compute store my prompts?

No. Prompts and model outputs pass through our servers and are not stored. We keep only billing records, such as token counts and cost.