Integrations
Anything that speaks the OpenAI chat API works. You need three values: base URL, key, model.
Base URL
https://uncensoredllm.xyz/v1
API key
your vk-... key
Model
venym/chimaera-1
OpenAI SDKs
Official Python and Node SDKs: set the base URL and key. Nothing else changes. See the quickstart.
Shell
export OPENAI_BASE_URL="https://uncensoredllm.xyz/v1"export OPENAI_API_KEY="vk-..."Both SDKs read those two environment variables, so unmodified code can switch by environment alone.
LangChain
Use the OpenAI chat class with a custom base URL.
script.pyPython
from langchain_openai import ChatOpenAI llm = ChatOpenAI(model="venym/chimaera-1", base_url="https://uncensoredllm.xyz/v1", api_key="vk-...")print(llm.invoke("Hello").content)LlamaIndex
Use the OpenAI-compatible LLM class (OpenAILike), since stock OpenAI validates model names against OpenAI's own list.
script.pyPython
from llama_index.llms.openai_like import OpenAILike llm = OpenAILike(model="venym/chimaera-1", api_base="https://uncensoredllm.xyz/v1", api_key="vk-...", is_chat_model=True)SillyTavern
- API: Chat Completion, source: Custom (OpenAI-compatible).
- Custom endpoint (base URL):
https://uncensoredllm.xyz/v1 - Custom API key: your
vk-key. - Model: enter
venym/chimaera-1, or pick it from the fetched list.
Open WebUI
- Admin settings, Connections, add an OpenAI API connection.
- URL:
https://uncensoredllm.xyz/v1. Key: yourvk-key. - Save, then pick
venym/chimaera-1from the model selector.
LibreChat
Add a custom endpoint in librechat.yaml:
YAML
endpoints: custom: - name: "UncensoredLLM" apiKey: "${UNCENSOREDLLM_API_KEY}" baseURL: "https://uncensoredllm.xyz/v1" models: default: ["venym/chimaera-1"] fetch: true titleConvo: true titleModel: "venym/chimaera-1"Editors and agents
Continue
YAML
models: - name: Chimaera 1 provider: openai model: venym/chimaera-1 apiBase: https://uncensoredllm.xyz/v1 apiKey: vk-...Cline and Roo Code
- API provider: OpenAI Compatible.
- Base URL:
https://uncensoredllm.xyz/v1. API key: yourvk-key. - Model ID:
venym/chimaera-1. Set the context window to the value on the models page.
Aider
Shell
export OPENAI_API_BASE="https://uncensoredllm.xyz/v1"export OPENAI_API_KEY="vk-..."aider --model openai/venym/chimaera-1The openai/ prefix tells Aider to use the OpenAI-compatible route. The rest is the UncensoredLLM id.
When something does not work
- Check the base URL ends in
/v1, with no trailing/chat/completions. - A 401 means the key was not sent or is wrong. A 404 on the model means the id is wrong. See errors.
- Clients that require a fixed list of OpenAI model names will not accept our ids. Use one with a custom model field.
- Menus and option names differ between client versions. If a field above has moved, look for the equivalent "base URL" and "API key" settings.