EN ▾
Get API key

Uncensored LLM API Documentation

Connect a Chat Completions client, send a saved dialogue request and inspect the response. This quickstart covers authentication, message structure, streaming, account limits and error handling.

per 1M input tokens
$0.15
Output tokens / 1M
$0.50
token context
100,000
trial credit
$0.50
requests per minute
300

Base URL and Authentication

To use the uncensored llm api, point your client to https://api.uncensoredllmapi.com/v1. Authentication relies on a single API key tied to your account. Generate this key on the Get API key page after signing up with an email and password. Pass the key via the Authorization: Bearer <key> header in every request. If the key is invalid or expired, you receive a 401 error. Note that regenerating the key revokes the old one immediately.

First Request

Send a POST request to /v1/chat/completions with the model ID uncensored. This model is an open-weight LLM tuned for unrestricted responses to lawful adult content. It does not use the GPT, Claude, or Gemini architectures. Include your message history in the messages array. The context window supports 100,000 tokens total for prompt and completion combined.

curl https://api.uncensoredllmapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python SDK Integration

Use the official OpenAI Python SDK to interact with the API. Set the base_url to our endpoint and provide your API key. The client automatically handles JSON serialization and retry logic. This approach works for simple text generation or complex roleplay scenarios where content filters are not desired. Ensure your SDK version is recent enough to support the streaming parameters if needed.

from openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredllmapi.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 SDK Usage

For JavaScript or TypeScript projects, initialize the OpenAI client with the custom base URL. The Node SDK behaves identically to the Python version regarding authentication and request structure. You can send standard chat completions or function calls. The uncensored model responds to standard tool definitions without blocking based on topic sensitivity. Monitor your usage dashboard to track credit consumption against the prepaid balance.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredllmapi.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 Responses

Enable streaming by setting stream: true in your request. The server returns a Server-Sent Events (SSE) stream containing partial token deliveries. This reduces perceived latency for chatbot interfaces. Each chunk contains a delta of the generated text. Process these chunks to update your UI in real-time. The uncensored AI API maintains the same token limits and pricing for streamed responses as for synchronous requests.

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)

Limits, Errors, and Context

Full keys allow 300 requests per minute and 8 concurrent requests; trial keys allow 60 per minute and 2 concurrent requests. Request bodies are limited to 8 MB. Combined input and output must fit within 100,000 tokens. Handle rate limits, insufficient credit and content refusals in the client.

What the API supports

A quick checklist for developers: format, limits, features, billing.

SpecValue
API formatOpenAI Chat Completions schema; official openai SDKs work unchanged
Model IDuncensored
API keyAuthorization: Bearer YOUR_KEY
Base URLhttps://api.uncensoredllmapi.com/v1
EndpointsPOST /v1/chat/completions · GET /v1/models
SSE streamingSupported (stream: true), usage included at the end
Context window100,000 tokens (prompt + completion together)
Structured outputresponse_format: {"type": "json_object"}
Completion lengthprompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap
Function callingSupported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages
Other parameterstemperature, top_p, stop, seed and the two penalties are passed through
Concurrencyup to 8 in parallel per key
HeadersX-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency
Request size8 MB request body
Rate limit300/min per key
Trial credit$0.50 of credit valid 7 days, no card needed · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up
Credit expiryno monthly fee; paid credit does not expire
Token pricesinput $0.15 / 1M tokens, output $0.50 / 1M tokens
PaymentUSDT (TRC20) or USDC (Base), any whole amount from $20 to $500
Billingpay as you go from prepaid credit; nothing is charged for failed or refused requests
Volume bonus+5% on $50+, +10% on $100+, +15% on $200+
Keysone key per account, regenerate any time (the old one stops working)
Content policyuncensored for adults; the only hard rule: no sexual content involving minors
Sign-inGoogle or e-mail and password

Error reference

Every error is JSON with a type you can switch on. You are never charged for an error.

HTTPTypeWhat to do
400bad_requestmalformed request or too long for the context window
401missing_key · invalid_key · key_revokedno key, wrong key, or a key replaced by a newer one
402no_creditout of credit; add credit and retry
403content_blockedrefused by the content policy
404not_foundonly /v1/chat/completions and /v1/models exist
413request_too_largebody over 8 MB
429rate_limited · concurrencyslow down: rate or parallel limit reached
503upstream_busymodel busy — retry in a few seconds

Questions and answers

Does regenerating my API key reset the rate limit?

No. The rate limit of 300 requests per minute applies to your account, not just the key string. Generating a new key revokes the old one but does not give you a fresh limit.

Is this API suitable for high-volume production?

Assess the endpoint against your application’s requirements using saved test requests. Check response format, error handling, measured latency and token usage. Paid credit does not expire; trial credit has a 7-day validity period. Do not assume an SLA or other certification unless it is explicitly offered.

What happens if I run out of credits?

Requests will return a 402 error. You must top up your account to resume service. Credits are prepaid and do not expire, but you cannot make requests until funds are available.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.