Uncensored LLM API Quickstart

Base URL and Authentication

The API key authenticates every request to our endpoint. You receive a single key upon signup via Google or email, and it remains active until you generate a replacement. Use the base URL https://api.alternativeopenrouter.com/v1 to point your existing OpenAI SDK clients directly at our infrastructure. We do not route between multiple vendors; we serve one uncensored open-weight model optimized for direct communication without content refusals for lawful adult use. Base URL: https://api.alternativeopenrouter.com/v1 Header: Authorization: Bearer YOUR_API_KEY Model ID: uncensored

First Request

Send a standard chat completion request to generate text from our model. The endpoint accepts the same JSON structure used by major providers, ensuring your existing code works without modification. You pay only for tokens consumed, with errors and refusals (except for the minor child safety limit) charged at zero. Price: $0.15 per 1M input tokens, $0.50 per 1M output tokens.

Copycurl https://api.alternativeopenrouter.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the capital of France"}]
  }'

Python SDK Integration

Use the official Python library to interact with our API seamlessly. Configure the client with your key and the specific base URL to bypass any default routing. This approach lets you leverage familiar async patterns while accessing our uncensored model directly. Ensure you pass the model ID as uncensored to route to our server. Context Window: 100,000 tokens (prompt + completion combined).

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.alternativeopenrouter.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 SDK Usage

Integrate the API into your JavaScript or TypeScript applications using the standard Node client. Set the base URL to direct traffic to our uncensored endpoint, ensuring you get the expected raw responses without external filtering. This setup is ideal for agent pipelines that require reliable, low-latency text generation. Max Output: 16,000 tokens per request (2,048 if unspecified).

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.alternativeopenrouter.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 Responses

Enable streaming by setting stream: true in your request. The API returns a Server-Sent Events (SSE) stream, delivering tokens as they are generated. This reduces perceived latency for end-users and allows for real-time display of the model's output. Token usage statistics are included in the final chunk of the stream. Feature: Streaming via SSE with token usage in the last chunk.

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)

Rate Limits and Constraints

Each API key is limited to 300 requests per minute and 8 concurrent requests. The request body size must not exceed 8 MB. If you exceed these limits, the API returns a 429 error. Authentication failures return 401, and insufficient credit returns 402. The context window is 100,000 tokens total, meaning your prompt and completion share this space. Errors do not consume credit, so retrying failed requests is safe.