Start with uncensored ai

Prerequisites: SDK and base URL

Install your preferred SDK and point it to our base URL. We support standard OpenAI-compatible clients, so you likely already have the tools needed. You will need an API key from the dashboard. Change the base URL to our endpoint. This ensures all requests route correctly to our servers.

• Install the SDK for your language.
• Create an account and generate a key.
• Set the base URL to https://api.uncensoredlink.com/v1.

Copycurl https://api.uncensoredlink.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Run npm install react"}]
  }'

No complex setup is required. Just configure the client with your key and the correct endpoint. This keeps your integration simple and direct.

Authenticate with your API key

Pass your API key in the Authorization header for every request. This verifies your identity and grants access to the uncensored model. Without a valid key, the API returns a 401 error. Generate your key from the dashboard page. It appears immediately after signup. Use this key in all subsequent calls. Keep it secure. Do not share it publicly. One key per account is standard. Replace the old key if you generate a new one. This ensures clear usage tracking. Your privacy remains intact. Only your email is required for the account.

Send your first chat completion

Send a POST request to /v1/chat/completions with your message. The model responds with text directly. This is a straightforward text-in, text-out interface. Use the model ID uncensored. This ID routes to our dedicated tuned model. It handles adult content without refusal. You can set parameters like temperature. Adjust these to control creativity. The response includes the generated text. Check the usage details in the response. This helps you track token consumption. Errors are free. Only completed tokens count. Start with a simple prompt. Test the connection. Verify the output quality. This confirms your setup works correctly.

Enable streaming for real-time output

Set the stream parameter to true for real-time results. The API sends tokens as they are generated. This improves user experience for long responses. Receive partial results instantly. Handle each chunk as it arrives. Update your UI continuously. This creates a smooth typing effect. The final chunk contains the total token usage. Use this to update your balance display. Streaming works with all standard parameters. You can still control temperature and top_p. This feature is essential for chat interfaces. It reduces perceived latency significantly. Your clients must handle SSE properly.

Use function calling and JSON mode

Define tools in your request for structured output. The model can call functions based on your prompt. This enables complex agent workflows. Use JSON mode for strict schema compliance. Set response_format to json_object. This ensures predictable parsing. Combine tools with JSON mode for robust apps. The model understands tool definitions clearly. Pass the tool results back to the model. It continues the conversation contextually. This supports advanced automation tasks. Keep your tool schemas simple. Complex schemas may confuse the model. Test with simple examples first. Verify the output format matches your expectations. This ensures reliable integration.

Handle tokens and usage limits

Monitor your token usage and request limits closely. The context window is 100,000 tokens total. This includes both input and output tokens. Your output is capped at 16,000 tokens per request. Errors do not consume credits. Rate limits are 300 requests per minute. You can have 8 concurrent requests. The request body must be under 8 MB. If you exceed limits, you get a 429 error. Check your balance regularly. Top up with crypto when needed. Credit never expires. Mistakes are fixed via support. This ensures uninterrupted service.

Python

Copyfrom openai import OpenAI

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