Base URL and Authentication
Connect to our openai compatible API by updating your client configuration to point at https://api.openaicompatibleapiendpoints.com/v1. You need a valid API key sent in the Authorization header as a Bearer token. This setup works with the official OpenAI SDKs and any compatible client library. No complex gateway configuration is required.
curl https://api.openaicompatibleapiendpoints.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Return 500 status code"}]
}'Every request must include your unique key. If the key is missing or invalid, the server returns a 401 error immediately. This ensures your calls reach the correct uncensored LLM without routing delays.
Chat Completions Endpoint
Send messages to the POST /v1/chat/completions endpoint to get text responses from the uncensored model. This endpoint handles standard conversational turns and supports up to a 100,000 token context window. You can set a maximum output of 16,000 tokens per request. The model answers without content refusals for lawful adult topics.
from openai import OpenAI
client = OpenAI(base_url="https://api.openaicompatibleapiendpoints.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)Use the standard messages array format. The API ignores extra fields it does not recognize, making migration easy. You only pay for tokens actually consumed by the model.
Streaming Responses
Enable real-time token delivery by setting stream: true in your request. The server sends a series of Server-Sent Events (SSE) until the response completes. Token usage statistics appear in the final chunk of the stream. This reduces perceived latency for users waiting for long answers.
stream = 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)Buffer the incoming tokens on the client side to reconstruct the full text. Errors during streaming are rare but should be handled by checking the final event for an error code. The stream stops automatically when the context limit or max tokens are reached.
JSON Mode and Tools
Force structured output by setting response_format to {"type": "json_object"}. This ensures the model returns valid JSON instead of markdown text. You can also use the tools parameter for function calling. The API supports tool_choice for precise control over which functions the model invokes.
Use temperature and top_p to adjust randomness. Set seed for reproducible results during debugging. These parameters work exactly as expected in standard OpenAI-compatible integrations.
Error Handling and Limits
Handle standard HTTP errors to manage client-side failures gracefully. A 401 status means your API key is invalid. A 402 status indicates your prepaid credit is exhausted. A 429 error signals that you have exceeded the 300 requests per minute limit.
Each key allows eight concurrent requests. The request body is capped at 8 MB. Refunds are not issued for used credit, but errors during processing are free. Always check the error object in the JSON response for details.
Context Window and Model Details
The model supports a 100,000 token context window for both prompt and completion combined. This allows deep context retention for long documents or extended conversations. The default max output is 2,048 tokens if you do not specify max_tokens. You can increase this up to 16,000 tokens per request.
The model is not GPT, Claude, or any other vendor model. It is an open-weight model tuned for uncensored responses. No data from your prompts is used for training. This ensures privacy for your proprietary data.
Node.js
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.openaicompatibleapiendpoints.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);