Integrate the Uncensored AI Model API

Authentication and Base URL

Our API is designed as a drop-in replacement for existing OpenAI clients. You only need to change two variables: the base_url and your api_key. The base URL for all requests is https://api.llmmodelsapi.com/v1. Authentication is handled via the Authorization header using a Bearer token. Ensure you keep your API key secure, as it grants access to your prepaid credit. You can regenerate your key at any time from your dashboard, which immediately revokes the old one.

First Request

Send a standard chat completion request to test connectivity. Use the model ID uncensored to access our purpose-built large language model. This model is tuned to answer without content refusals for lawful adult use, making it ideal for agents that need consistent outputs. The request body follows the standard OpenAI chat completions format.

Copycurl https://api.llmmodelsapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Verify the response includes a valid completion. If you receive a 200 status code, your integration is working correctly. This ai model api endpoint supports both single-turn and multi-turn conversations within the context window.

Python SDK Integration

Using the official OpenAI Python SDK is the fastest way to integrate. Point the client to our base URL and provide your API key. The SDK handles serialization and connection pooling automatically. This approach works with any OpenAI-compatible client library that respects the base_url override.

Copyfrom openai import OpenAI

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

The Python SDK supports streaming and synchronous calls. For most agent workflows, synchronous calls are simpler, but streaming is available if you need to display tokens as they generate. The model ID remains uncensored regardless of the SDK version.

Node SDK Integration

For JavaScript and TypeScript environments, the Node SDK follows the same pattern. Initialize the client with the correct base URL and credentials. This ensures your existing codebase requires minimal changes to switch providers. The uncensored model ID is compatible with all standard chat completion parameters.

Copyimport OpenAI from "openai";

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

The Node SDK also supports async/await patterns, making it easy to integrate into Express routes or serverless functions. Keep your API key in environment variables to prevent accidental exposure. This openai compatible api design means you can swap back to OpenAI or switch to other providers by changing only the configuration object.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns a Server-Sent Events (SSE) stream, allowing you to process tokens as they are generated. This reduces perceived latency for end-users and is essential for real-time agent interactions. The stream format is identical to the OpenAI SSE specification.

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)

Each chunk contains partial delta data. You must accumulate these deltas to reconstruct the full response. Streaming does not affect pricing; you are charged for the total input and output tokens regardless of streaming mode. This feature is part of the robust chat completions api design we provide.

Limits, Errors, and Context

Our infrastructure enforces strict limits to ensure reliability. You are limited to 300 requests per minute per key, with a maximum request body size of 8 MB. The context window is 64,000 tokens, shared between prompt and completion. If you exceed the rate limit, you will receive a 429 error. An invalid key returns 401, and insufficient credit returns 402. Unlike many llm api provider options, we do not hide these limits; they are transparent and consistent. No training is performed on your data, and privacy is maintained by not using prompts for model improvement.