API Documentation: Uncensored LLM

Authentication and base URL

The base URL is HTTPS://api.webtheon.com/v1. Pass your API key in the Authorization header. The key is shown immediately after creation. Use it with any standard OpenAI SDK.

Chat completions endpoint

Send messages to POST /v1/chat/completions. The model ID is uncensored. This endpoint handles text generation only. No images, no audio, no embeddings.

Requests must stay under 8 MB. The context window spans 100,000 tokens total. This includes both prompt and completion tokens combined. Output is capped at 16,000 tokens per request. You can adjust this limit using the max_tokens parameter.

Model listing endpoint

Query GET /v1/models to verify availability. This endpoint returns metadata about the uncensored model. It confirms the model ID and supported parameters. Use this to debug client configurations quickly.

The response includes the model ID, object type, and owned by field. This helps you ensure your client library is pointing to the correct service. It is a simple health check for your integration.

Streaming and token usage

Enable streaming by setting stream: true. Responses come as Server-Sent Events (SSE). Token usage details appear in the final chunk of the stream.

This approach reduces perceived latency for long outputs. You can begin processing text as it arrives. It is ideal for real-time interfaces. The stream ends cleanly with usage data.

Parameters and options

Support includes temperature, top_p, stop sequences, seed, and penalties. You can enforce JSON mode via response_format. Function calling (tools) is fully supported.

Set temperature for creativity. Adjust top_p for nucleus sampling. Use seed for reproducible outputs. These parameters give you precise control over generation quality. The model responds to standard OpenAI parameter names.

Error handling and limits

Rate limits are 300 requests per minute. Concurrency is capped at 8 simultaneous requests per key. Request bodies cannot exceed 8 MB.

Handle errors gracefully. A 401 status means your key is invalid. A 402 status indicates insufficient credit. A 429 status signals rate limiting. Errors are free, so they do not consume your prepaid tokens. This protects your balance during debugging.

cURL

Copycurl https://api.webtheon.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the capital of france"}]
  }'

Python

Copyfrom openai import OpenAI

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

Node.js

Copyimport OpenAI from "openai";

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

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)