API Reference: Chat Completions

Base URL and Authentication

Use the provided base URL to route requests to our uncensored LLM. Include your API key in the Authorization header for every request. This ensures your calls are authenticated and billed correctly to your prepaid credit. You can generate a key instantly via Google or email on the signup page.

Copycurl https://api.abliteratedllmonline.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the python dependencies for this flask app"}]
  }'

The endpoint accepts standard JSON payloads. If you use a third-party client, update the base URL to point here. Your API key acts as the sole credential for your account.

Chat Completions Endpoint

Send messages to the POST /v1/chat/completions endpoint to generate text. The model ID is always uncensored. This endpoint handles text input and returns text output without extra modalities. It is designed for roleplay, writing, or coding tasks that require no refusals.

Copyfrom openai import OpenAI

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

Configure your client library with the correct base URL. The SDK handles the JSON serialization for you. You can stream responses or wait for the full completion. The model runs on our servers, so you do not need local GPU resources.

Streaming Responses and Token Usage

Enable streaming by setting stream: true in your request. The API returns chunks via Server-Sent Events. The final chunk contains the total token usage statistics. This allows you to track costs in real-time without extra API calls. Streaming is ideal for interactive applications where latency matters.

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)

Parse the stream to display tokens as they arrive. The last chunk includes the usage object. You can accumulate these counts for your own billing dashboard. Errors during streaming are handled gracefully.

Function Calling and JSON Mode

Use the tools parameter for function calling. The model supports structured output via response_format set to json_object. This ensures consistent parsing for your backend logic. You can define complex schemas for your application.

Copyimport OpenAI from "openai";

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

Define your functions in the request body. The model will invoke them or return JSON data. This feature works with the uncensored model just like standard OpenAI APIs. You can mix tools and JSON mode as needed.

Rate Limits and Error Codes

The API enforces strict limits to ensure stability. You can make 300 requests per minute and 8 concurrent requests per key. The request body must not exceed 8 MB. Errors return standard HTTP status codes. A 401 error means your key is invalid. A 402 error indicates insufficient credit. A 429 error signals you have hit the rate limit.

Model Parameters and Context Window

The context window supports 100,000 tokens for prompt and completion combined. You can set temperature, top_p, and seed for control. Max output is 16,000 tokens per request. These parameters allow fine-tuning of creativity and determinism. Adjust settings based on your use case.

Copycurl https://api.abliteratedllmonline.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the python dependencies for this flask app"}]
  }'

Pass these parameters in the JSON body. The model responds according to your settings. Use seed for reproducible results. The uncensored model respects these constraints just like any other LLM.

Cost Calculation and Token Counts

Pay only for what you use. The rate is $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free. Your prepaid credit never expires. You can top up with crypto anytime. The API returns token counts in every response. Track your usage via the usage object.

Copycurl https://api.abliteratedllmonline.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the python dependencies for this flask app"}]
  }'

Monitor your balance on the dashboard. Credit is charged after each request. No monthly fees or subscriptions. You can start with a free trial. Use the API confidently without hidden costs.