First request in five minutes

Prerequisites and Authentication

Before sending requests, you need an API key. Sign up via Google or email on the Get API key page to generate your credential instantly. No phone number or payment method is required for the initial trial credit of $0.50, which expires in seven days. For sustained use, top up with USDT (TRC20) or USDC (Base). Your requests are authenticated by passing this key in the Authorization header.

We adhere strictly to the OpenAI protocol. This means you do not need a new client library; you simply point your existing OpenAI SDK to our base URL: https://api.ollamaapi.cc/v1. The model identifier is uncensored. This approach allows you to swap in our uncensored LLM without rewriting your application logic.

Send Your First Request

Start by verifying connectivity with a simple chat completion. The following curl command demonstrates how to structure the POST request to our endpoint. Note that the context window supports 64,000 tokens total, with a default maximum output of 2,048 tokens unless you specify max_tokens.

If you encounter a 401 error, verify your API key is correct. A 402 error indicates your prepaid credit is exhausted. A 429 error means you have hit the rate limit of 300 requests per minute.

Configure Python SDK

The official OpenAI Python SDK works directly with our API. Initialize the client by providing your API key and overriding the base_url parameter. This ensures all subsequent calls route to our uncensored model endpoint instead of the standard OpenAI servers.

Ensure you are using a recent version of the SDK that supports the base_url configuration. This setup is identical to connecting to any OpenAI-compatible service, making migration straightforward for developers already familiar with the Python client.

Configure Node SDK

For JavaScript and TypeScript developers, the @anthropic-ai/sdk or the official openai package can be configured similarly. Set the apiKey and baseUrl properties in your client initialization. This allows you to leverage the same robust tooling and type definitions you are used to, while benefiting from our uncensored model's output.

Remember that our model ID is always uncensored. Do not attempt to use other model identifiers unless they are explicitly supported in future updates. The SDK handles the JSON serialization and HTTP transport for you.

Enable Streaming Responses

For lower latency and better user experience, enable streaming by setting stream: true. Our API returns Server-Sent Events (SSE), allowing you to process tokens as they are generated. This is particularly useful for long-form content generation where waiting for the full response would cause noticeable delays.

Each chunk contains partial content. The final chunk includes the token usage statistics for the request. Streaming does not affect pricing; you are still charged for the total input and output tokens consumed.

Function Calling and JSON Mode

Our uncensored LLM supports function calling via the tools parameter, allowing your application to trigger specific actions based on user intent. You can also enforce strict JSON output by setting response_format to {"type": "json_object". This is ideal for structured data extraction or programmatic control flows.

When using JSON mode, ensure your prompt clearly instructs the model to output valid JSON. Errors in JSON formatting are not retried automatically, so handle parsing exceptions in your client code. Parameters like temperature, top_p, and seed are fully supported for fine-tuning output randomness.

cURL

Copycurl https://api.ollamaapi.cc/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."}]
  }'

Python

Copyfrom openai import OpenAI

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