Is the local AI uncensored model trained on my data?

No, your prompts are not used for training. Your privacy is maintained strictly. We do not sell your data to third parties. Your conversations remain yours.

What happens if I exceed the rate limit?

You receive a 429 error code. Requests are limited to 300 per minute per key. Wait a few seconds and retry. You can use multiple keys if needed.

Does the uncensored AI API support image generation?

No, this is a text-only API. You cannot generate images or audio. It serves large language model text responses exclusively. Use other services for media generation.

Uncensored AI API Quickstart Guide

Authentication & Base URL

Your API key authenticates every request. Use https://api.uncensoredailocal.com/v1 as your base URL. Headers require Authorization: Bearer YOUR_API_KEY. This setup works with any OpenAI-compatible client. You get one active key per account. Regenerate it instantly if needed. No phone number is required for signup. Just use Google or email to start.

Sending Your First Chat Completion

Send a POST request to /v1/chat/completions with your message. The model ID is always uncensored. This open-weight model answers without content refusals for lawful adult use. You get text in, text out. No images or audio are generated here. Use this endpoint for pure text interactions. It is simple and direct.

curl https://api.uncensoredailocal.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Translate this text to Spanish and keep the tone casual"}]
  }'

Enabling Streaming Responses

Stream tokens using Server-Sent Events. Set stream: true in your payload. Each chunk contains partial text. The final chunk includes total token usage. This allows real-time display of generated content. It reduces perceived latency significantly. Handle network interruptions gracefully. Streaming is essential for chat interfaces.

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)

Configuring JSON Mode

Force structured output for reliable parsing. Set response_format to {"type": "json_object"}. The model returns valid JSON every time. This is perfect for data extraction tasks. You avoid regex headaches. Ensure your schema is strict. Validation happens on your side. This feature ensures consistency.

import OpenAI from "openai";

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

Using Function Calling

Define tools in your request. The model selects functions based on context. Pass tools and tool_choice parameters. This enables agentic workflows. The model returns function names and arguments. You execute the function and feed results back. This creates powerful automation loops. It supports complex decision trees.

from openai import OpenAI

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

Understanding Token Costs

Pricing 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 get a 100,000 token context window. Max output is 16,000 tokens per request. Rate limits are 300 requests per minute. Check your balance in the dashboard. Crypto top-ups add bonus credit.

Uncensored AI API Quickstart