Method

AI without restrictions: three ways to use it today

You can use AI without restrictions through an API key in a chat app or coding agent, or by running open weights on a local GPU. The table shows what each route gives you.

Updated November 18, 2026

Three routes

RouteLargest modelContextYou payYou need
Chat app with an API keyKimi K3.1 Pro, 2,780B1,048,576Per token, credits from $5An API key
Coding agentKimi K3.1 Pro, 2,780B1,048,576Per token, or a plan from $10 a monthAn API key and the agent
A local GPUQwen 3.6 35B-A3B Abliterated, 36B262,144The hardwareOne 24 GB GPU

Set one up

Chat app

  1. Open the app's model settings, for example Open WebUI.
  2. Pick OpenAI Compatible as the provider.
  3. Set the base URL to https://api.silkcompute.com.
  4. Paste your key and a model id such as kimi-k3.1-pro-uncensored.

Coding agent

  1. Claude Code reads ANTHROPIC_BASE_URL.
  2. Set it to https://api.silkcompute.com.
  3. Codex and OpenCode take the same base URL in their config.

A local GPU

  1. Install Ollama from ollama.com.
  2. Run one command:
ollama run hf.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF

Limits that remain

Silk Compute's Terms forbid sexual content involving anyone under 18. Refusal behavior is removed, and models are served without content filters.