API Documentation

Base URL and Authentication

The API lives at https://api.ollamauncensoredmodels.com/v1Authorization header with your Bearer token. This setup works with any OpenAI-compatible client library because we adhere to the same authentication patterns. You can generate your key instantly via Google or email without providing a phone number. The system issues one active key per account, replacing any previous key immediately upon generation. This ensures consistent access without the need to manage multiple credentials simultaneously.

Making Your First Request

Send a POST request to /v1/chat/completions with the model ID set to "uncensored". The endpoint accepts standard parameters like messages, temperature, and max_tokens. It returns JSON responses containing the generated text and token usage statistics. You can test connectivity quickly by verifying the model list or sending a simple prompt. This direct approach removes the complexity of proxying or routing logic often found in other services.

Copycurl https://api.ollamauncensoredmodels.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the output for 2 plus 2"}]
  }'

Python SDK Integration

Use the official OpenAI Python library to connect by overriding the base URL. Set the API key and base URL attributes before making any calls. This allows you to leverage existing codebases without rewriting client logic. The library handles serialization and error parsing automatically. You can stream responses or request synchronous completions depending on your application's latency requirements. This method ensures compatibility with standard development practices used across the industry.

Copyfrom openai import OpenAI

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

Initialize the OpenAI client with your base URL and API key in Node.js environments. Pass the model identifier "uncensored" to the chat completions method. The SDK manages the HTTP requests and parses the JSON responses efficiently. You can integrate this directly into Express routes or serverless functions. The code structure mirrors standard OpenAI implementations, making migration from other providers straightforward. This approach maintains type safety and error handling consistent with modern JavaScript development.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.ollamauncensoredmodels.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 and Token Usage

Enable streaming by setting stream: true in your request. The server returns Server-Sent Events (SSE) for real-time token delivery. Token usage details appear only in the final chunk of the stream to keep overhead minimal. This allows you to display responses progressively to users without waiting for the entire generation. You can track cumulative token counts for billing transparency. Streaming is ideal for chat interfaces where immediate feedback enhances the user experience significantly.

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)

Limits, Errors, and Context

Each API key supports 300 requests per minute and eight concurrent connections. The request body size limit is 8 MB, and the context window spans 100,000 tokens total. Errors like 401 indicate an invalid key, while 402 signals insufficient credit. A 429 status means you have hit the rate limit. The model refuses only sexual content involving minors, ensuring broad applicability for adult use cases. Credit never expires, so you can pause usage between projects without losing funds. This predictable structure helps you plan capacity for high-traffic applications effectively.