API Documentation: uncensored text model

Response format: Streaming SSE & JSON mode

Receive responses as Server-Sent Events (SSE) when streaming is enabled, or as a single JSON object if streaming is disabled. Streaming allows you to display tokens as they are generated, reducing perceived latency for long outputs. You can force structured output by setting response_format to {"type": "json_object"}, which is ideal for programmatic integration.

The final chunk of a streaming response includes the complete token usage statistics, allowing you to track costs in real-time. Errors are returned as standard HTTP status codes with a JSON error object containing a code and message.

Model parameters: temperature, top_p, and seed

Control the randomness and reproducibility of your outputs using standard LLM parameters. Set temperature between 0 and 2 to adjust creativity, with lower values yielding more deterministic results. Use top_p for nucleus sampling, typically set between 0.1 and 1.0, to control the diversity of token selection.

The seed parameter allows you to reproduce identical outputs for testing and debugging. These parameters apply to the uncensored model running on our servers, ensuring consistent behavior across requests. Adjust these values to fine-tune the tone and precision of the generated text.

Function calling (tools) support

Enable tool usage by passing a tools array in your request body. The API supports standard OpenAI-style function definitions, allowing you to define custom schemas for structured data extraction or action execution. Use tool_choice to specify whether the model should automatically choose a tool, force a specific one, or disable tool usage entirely.

This feature is particularly useful for building agents or automating workflows with uncensored logic. Ensure your tool definitions adhere to the JSON schema format, and the API will handle the parsing and response formatting automatically.

Rate limits and constraints

Each API key is limited to 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB, and the context window supports up to 100,000 tokens for prompt and completion combined. Output is capped at 16,000 tokens per request, or 2,048 if max_tokens is not specified.

Common errors include 401 for invalid keys, 402 for insufficient credit, and 429 for rate limit exceeded. These limits ensure fair usage across all users. Monitor your usage via the dashboard to avoid interruptions.

cURL

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

Python

Copyfrom openai import OpenAI

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