Uncensored API Quickstart

Installation and setup

Start by obtaining your API key from the dashboard and configuring your client with the base URL. The endpoint is https://api.ollamaapikey.com/v1, which works with any OpenAI-compatible library by simply updating the base URL and providing your key.

Authentication is straightforward. Pass your key in the Authorization header as a Bearer token. You can generate a new key instantly via Google or email, and it remains active until you replace it. No monthly fees or expiration dates apply to your prepaid credit.

Your first request

Send a standard chat completion request to receive a text response from the uncensored model. Use the POST /v1/chat/completions endpoint with the model ID set to uncensored.

This model handles adult content and code without arbitrary refusals. The context window supports 100,000 tokens total, allowing long prompts and substantial outputs up to 16,000 tokens.

Here is a basic example using curl:

Copycurl https://api.ollamaapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a python script to parse log files"}]
  }'

Streaming responses

Enable streaming by setting stream: true in your request. This returns Server-Sent Events (SSE) for real-time token delivery. You can parse token usage from the final chunk in the stream.

Streaming is ideal for coding assistants or chat interfaces where immediate feedback improves user experience. The official OpenAI SDKs handle SSE parsing automatically in most languages.

Example streaming request in Python:

Copyfrom openai import OpenAI

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

Function calling

Supports function calling via the tools parameter. Define your function schema and let the model decide whether to call it. This works with both synchronous and streaming modes.

Pass tool_choice: auto to let the model decide, or specify a specific tool. The API follows standard OpenAI tool-calling conventions, making migration from other providers simple.

Node.js SDK example:

Copyimport OpenAI from "openai";

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

JSON mode

Force structured output by setting response_format: { "type": "json_object" }. The model will return valid JSON instead of free text.

This is useful for parsing data, generating config files, or feeding structured data into downstream applications. The model is optimized to follow these constraints reliably.

Error handling

Handle common errors gracefully. A 401 status indicates an invalid or expired key. A 402 status means your prepaid credit is exhausted; top up via crypto to continue. A 429 status signals rate limiting (300 requests per minute per key).

Errors are free, so you won’t be charged for failed requests. Your credit never expires, so you can top up at any time without losing balance.

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)