Integrate the uncensored LLM API

Set your base URL and API key

Point your client to our specific endpoint. Use https://api.openaicompatibleserver.com/v1 as your base URL. Generate a key via the dashboard. The key authenticates all requests.

Send your first chat completion

POST to the chat completions endpoint. Send your prompt and receive text. The model id is uncensored. It handles context up to 100,000 tokens.

Enable streaming and get real-time tokens

Set stream: true in your request. Receive Server-Sent Events. Token usage appears in the final chunk. This reduces perceived latency for long outputs.

Use function calling and JSON mode

Pass tools in the request body. The model follows strict JSON schemas. Set response_format to {"type": "json_object"} for reliable parsing. This ensures structured data for your applications.

Handle errors and usage limits

Check HTTP status codes for issues. A 401 means your key is invalid. A 402 indicates insufficient credit. A 429 signals rate limits. You get 300 requests per minute. The 100k context window includes prompt and completion.

Integrate with OpenAI compatible server clients

Replace your base URL in any SDK. Use the same Python or Node libraries. The protocol remains identical. This works with tools like Cline or Roo Code. Switch backends without rewriting code.

cURL

Copycurl https://api.openaicompatibleserver.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set the server timeout to 30 seconds"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openaicompatibleserver.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Node.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicompatibleserver.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)