Integration guide for uncensored completions

Prerequisites: SDK installation and environment variables

Install the official SDK for your language and export your credentials before making requests. You need an API key from our portal and the standard library for your chosen runtime. This ensures your code can authenticate against our endpoints immediately.

• Python: pip install openai
• Node.js: npm install openai
• Export OPENAI_API_KEY with your key from the dashboard.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.gptnsfw.cc/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)

Configuring the base_url and API key

Point your client to our dedicated endpoint to bypass standard model restrictions. Set the base_url to https://api.gptnsfw.cc/v1 and use the key you generated. This single change directs traffic to our uncensored infrastructure.

• Base URL: https://api.gptnsfw.cc/v1
• Model ID: uncensored

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.gptnsfw.cc/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);

Making your first POST /v1/chat/completions request

Send a standard completion request with your system and user prompts. The model returns text responses without the usual content filters for lawful adult topics. Use the uncensored model ID in your payload.

Copycurl https://api.gptnsfw.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return the full API response for the /v1/messages endpoint"}]
  }'

Handling streaming responses (SSE) and token usage

Stream tokens as they generate using Server-Sent Events for real-time output. The final chunk contains the total token usage for your request. This approach reduces perceived latency for long-form roleplay or story generation.

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)

Enforcing JSON mode for structured data outputs

Force the model to output valid JSON by setting response_format to {"type": "json_object"}. This is critical when parsing structured data or feeding results into other applications. The model adheres to this format strictly without adding conversational filler.

Configuring temperature, top_p, and stop sequences

Adjust temperature and top_p to control creativity or determinism in your outputs. Use stop sequences to halt generation at specific markers. These parameters give you precise control over the uncensored chatbot's behavior.