Uncensored ollama API Reference

Base URL and Authentication

The base URL for all requests is HTTPS://api.uncensoredollama.com/v1. You authenticate by passing your API key in the Authorization header. The header format must be exactly 'Bearer YOUR_API_KEY'. This key is generated immediately after you sign up via Google or email. There is no phone number verification required. Your key works with any standard OpenAI SDK client.

First Request

Send your first prompt to the /v1/chat/completions endpoint. The model ID is 'uncensored'. This model answers without content refusals for lawful adult use. It is not GPT or Claude. Use the following curl command to verify connectivity.

Copycurl https://api.uncensoredollama.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list 3 common rust compile errors"}]
  }'

Expect a JSON response with the generated text. If you receive an error, check your key validity. The model handles complex instructions well. You can adjust parameters like temperature for more creative outputs.

Python SDK Integration

Use the official OpenAI Python library for easy integration. Set the base_url and api_key attributes on the client instance. This allows you to reuse existing code structures. The following example demonstrates a simple chat completion call.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredollama.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 response object contains the generated text in the choices array. You can extract the content directly. This method is reliable for batch processing. It handles retries automatically.

Node SDK Usage

Initialize the OpenAI client with your credentials. The base_url must point to our endpoint. This ensures compatibility with standard Node.js applications. Use the following snippet to create a client instance.

Copyimport OpenAI from "openai";

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

Call the chat.completions.create method with your model ID. The 'uncensored' model responds to system prompts effectively. You can stream results or wait for the full response. Error handling should catch network issues.

Streaming and Usage Data

Enable streaming by setting stream to true. This returns chunks as they are generated. The final chunk contains usage statistics. This includes input and output token counts. This data is crucial for billing accuracy.

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)

Process each chunk to build the complete response. The streaming feature reduces perceived latency. It works well for real-time applications. The token usage is only in the last chunk.

Limits and Errors

You are limited to 300 requests per minute per key. The context window is 100,000 tokens. Errors include 401 for invalid keys and 402 for insufficient credit. The 429 error indicates rate limiting. Handle these codes gracefully in your application. Refusals do not consume credit. Errors are free. Your prepaid credit never expires.