Uncensored llm api documentation

Base URL and Authentication

Connect immediately by pointing your client to our base URL and passing your key in the header. Authentication is straightforward: include Authorization: Bearer YOUR_API_KEY with every request. You get your key instantly after signing up with Google or email. No phone number is required, and the key appears on screen right away. This setup works with any standard OpenAI-compatible SDK because we follow the same interface structure. You do not need to manage complex login sessions or deal with session expirations that plague other platforms. Your key is the only credential you need for all endpoints. This simplicity means you can integrate the API into your scripts or applications without worrying about token refresh cycles or OAuth flows. The service is designed for developers who want direct access without bureaucratic hurdles. We provide a clean, predictable interface that behaves exactly like the industry standard. This reduces integration time significantly compared to wrestling with proprietary login systems.

Chat Completions Endpoint

Send messages to the uncensored model using the standard chat completions endpoint. The endpoint accepts POST requests to /v1/chat/completions with a JSON body containing your messages. You must specify the model id as uncensored to use our specific large language model. The system returns text responses that you can process or display. This is a text-in, text-out API with no image or audio generation capabilities. You control the tone and style by adjusting parameters like temperature or top_p. The response format is consistent and predictable, making it easy to parse in any language. You can send multiple turns in a single request to maintain conversation history. This approach mimics the behavior of major providers while offering our specific uncensored model. It is the core functionality for building chatbots, assistants, or content generators. The endpoint is optimized for speed and reliability.

Python SDK Integration

Integrate quickly using the official Python SDK with minimal configuration. You just need to set the base URL and API key in your client initialization. The code snippet below shows how to create a simple chat completion request. This method works seamlessly with existing OpenAI codebases because the interface is identical. You can pass a list of messages with roles like system, user, or assistant. The response object gives you access to the generated text and token usage. This makes debugging and monitoring your application straightforward. You do not need to write custom HTTP clients or handle JSON serialization manually. The SDK handles all the heavy lifting for you. This reduces boilerplate code and speeds up development cycles significantly. You can start prototyping in minutes and scale later when needed. The library is well-documented and actively maintained.

Node SDK Integration

Use the Node.js SDK to integrate the API into your JavaScript or TypeScript projects. The setup is similar to Python: configure the base URL and key once. The code example demonstrates a simple request to the chat endpoint. You can use the same message structure as in Python, ensuring consistency across your stack. The response object provides the completion text and usage statistics. This is useful for tracking token consumption in your Node applications. The SDK handles streaming and error handling internally, simplifying your code. You can integrate this into Express routes, serverless functions, or background jobs. The interface is familiar to anyone who has used the OpenAI Node library. This means you can reuse existing logic and patterns without learning a new API structure. It fits naturally into modern JavaScript ecosystems. You get the benefits of a standardized interface with our specific model capabilities. This reduces cognitive load when switching between different parts of your application.

Streaming Responses

Enable real-time output by setting the stream parameter to true in your request. The API returns a stream of chunks instead of a single complete response. This is ideal for chat interfaces where you want to show text as it is generated. Each chunk contains a partial response, allowing you to update the user interface incrementally. The final chunk includes the total token usage for the request. This feature works with both Python and Node SDKs with minimal code changes. You handle the stream by iterating over the chunks and appending the text. This creates a smoother user experience compared to waiting for the full response. It is particularly useful for long-form content generation or complex reasoning tasks. The streaming capability is standard in modern LLM APIs and is fully supported here. You can control the flow by managing the stream consumption rate. This gives you fine-grained control over how the output is displayed to the user.

Limits, Errors, and Context

The context window supports up to 100,000 tokens for prompt and completion combined. You can send up to 8 concurrent requests per key and 300 requests per minute. If you exceed these limits, you will receive a 429 rate limit error. Authentication errors return a 401 status if your key is invalid. A 402 status indicates that your prepaid credit is exhausted. You can top up with crypto at any time to resume service. Errors do not consume your credit, so failed requests are free. The maximum output per request is 16,000 tokens, or 2,048 if you do not specify a limit. Request bodies are capped at 8 MB. These limits are designed to ensure fair usage and system stability. You can monitor your usage through the response headers or SDK objects. This transparency helps you manage your budget and plan your application architecture effectively. The prepaid model means you only pay for what you use, with no hidden fees.

cURL

Copycurl https://api.mistralapilogin.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Fix my token expiry error"}]
  }'

Python

Copyfrom openai import OpenAI

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