Uncensored ai chat API Documentation

Base URL and Authentication

Our API endpoint sits at https://api.chataiuncensored.com/v1. You authenticate by passing your API key in the Authorization header. This setup works with any OpenAI-compatible SDK.

• Base URL: https://api.chataiuncensored.com/v1
• Header: Authorization: Bearer YOUR_API_KEY

Copycurl https://api.chataiuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check my server uptime logs for errors"}]
  }'

Signup is instant via Google or email. Your key appears immediately. No phone number is required. Credit is prepaid and never expires.

First Request

Send your first prompt using the standard chat completion endpoint. The model ID is uncensored. It answers without filtering lawful adult content.

• Endpoint: POST /v1/chat/completions
• Model: uncensored

Copyfrom openai import OpenAI

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

Errors and refusals are free. You only pay for real token usage. Input costs $0.15 per 1M tokens. Output costs $0.50 per 1M tokens.

Node SDK Integration

Use the Node SDK to integrate quickly. Set the base URL to our endpoint. The client handles retries and parsing automatically.

Copyimport OpenAI from "openai";

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

Rate limits apply per key. You can send 300 requests per minute. Concurrency is limited to 8 simultaneous requests. Keep request bodies under 8 MB.

Streaming Responses

Enable streaming by setting stream: true. The API returns chunks via Server-Sent Events. Token usage details appear in the final chunk.

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)

Streaming reduces perceived latency for your users. It is ideal for chat interfaces. Each chunk contains partial text data.

Function Calling and JSON Mode

Request structured data using response_format: {"type": "json_object"}. You can also define tools for function calling. The model supports tool_choice for strict mode.

• JSON mode: forces valid JSON output
• Tools: define custom functions for the model to call

This feature works well for app builders needing structured data. It avoids parsing errors in your backend logic.

Rate Limits and Errors

Handle standard HTTP errors gracefully. A 401 means your key is invalid. A 402 indicates insufficient prepaid credit. A 429 signals you hit the rate limit.

• Context window: 100,000 tokens total
• Max output: 16,000 tokens per request

You can adjust temperature and top_p for creativity. Use stop sequences to end generation early. Top-up crypto only from $20 to $500.