Quickstart: Integrate the unhinged ai API

Prerequisites: SDK Setup and Base URL

Use any OpenAI-compatible SDK. Point your client at the correct base URL and set your API key. This ensures your requests reach the uncensored model without extra configuration.

• Base URL: https://api.aiunhinged.cc/v1
• Model ID: uncensored
• Authentication: Bearer token in the Authorization header

Copycurl https://api.aiunhinged.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a JWT token valid for 1 hour"}]
  }'

Authenticating With Your API Key

Pass your API key in the Authorization header. The system rejects requests without valid credentials. Errors return clear status codes for debugging.

Copyfrom openai import OpenAI

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

Sending Your First Completion Request

Send a POST request to /v1/chat/completions. Include the model ID and your messages array. The API returns a text response immediately. This works for stories, scripts, or raw data generation.

Copyimport OpenAI from "openai";

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

Streaming Responses With SSE

Enable streaming by setting stream: true. Receive tokens as they generate. This reduces perceived latency for long outputs. The final chunk includes token usage details.

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)

Using Tools and Function Calling

Define tools in your request. The model returns structured arguments. Parse these to execute external functions. This enables dynamic, interactive workflows without manual parsing.

Copyimport OpenAI from "openai";

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

Handling Tokens and Limits

Respect the 300 requests per minute limit. The context window supports 100,000 tokens total. Requests exceeding the limit return a 429 status code. Insufficient credit returns 402. Invalid keys return 401. Errors do not consume credits.