Quickstart for Uncensored AI API
Immediate integration of the uncensored AI API for free language models. Use standard SDKs to generate text, support streaming and tool calling with a single key.
Authentication and API key
To start, register by entering only email and password on the dedicated page. No phone number or credit card is required for the initial free trial credit. Once registration is complete, your API key is displayed immediately. Use this key as the value of the Authorization header in every request. The key is unique per account and can be regenerated at any time, invalidating the previous one. Your account requires only an email and a password, ensuring essential privacy without superfluous data.
First Request
Our service is compatible with the OpenAI API. Send POST requests to https://api.apiiasenzacensura.com/v1 using the uncensored model. The context supports up to 100,000 tokens combining prompt and completion. Below is a basic example to send a prompt and receive a text response.
curl https://api.apiiasenzacensura.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."}]
}'
Questa è la base per l'api intelligenza artificiale che cerchi: semplice, diretta e senza complessità extra.
Python SDK
Se preferisci Python, utilizza il client ufficiale o qualsiasi SDK compatibile. Imposta la variabile d'ambiente OPENAI_API_KEY o passa la chiave direttamente all'inizializzazione. Il modello da specificare è uncensored. Questo approccio è ideale per script di automazione o applicazioni backend che richiedono una uncensored llm api robusta.
from openai import OpenAI
client = OpenAI(base_url="https://api.apiiasenzacensura.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)
The code above shows how to get a complete response. Note that the service does not offer embeddings or image generation, focusing exclusively on text.
Node.js SDK
Per gli sviluppatori Node.js, la logica è identica. Inizializza il client con la tua chiave e il base URL corretto. Il modello uncensored risponderà ai tuoi prompt senza le tipiche restrizioni etiche dei grandi provider. Questo rende la nostra api uncensored perfetta per integrazioni veloci in ambienti JavaScript moderni.
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.apiiasenzacensura.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);
The response will be a standardized JSON object, consistent with OpenAI developers' expectations.
Streaming Responses with SSE
For a smooth user experience, enable streaming by setting stream: true. The server will send text fragments via Server-Sent Events (SSE). This is essential for real-time chat applications. Streaming is natively supported with both curl and Python and Node SDKs.
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)
Handle the data events to accumulate the full response as it appears. Perceived latency decreases significantly with this technique.
Limits, Errors and Context
Ogni chiave è limitata a 300 richieste al minuto e un payload massimo di 8 MB. Gli errori comuni includono: 401 per chiave non valida, 402 per credito insufficiente e 429 per superamento del rate limit. Il contesto è di 100.000 token totali. Se ricevi un errore 402, ricarica il credito minimo di $10. La nostra ia senza filtri blocca solo i contenuti sessuali minori, permettendo altrimenti ogni tipo di contenuto adulto legale.
API specifications
If your tool speaks the OpenAI API, these are the details that matter.
| Feature | Support |
|---|---|
| API format | OpenAI-compatible: any OpenAI SDK or client works — change the base URL and the key |
| Endpoints | POST /v1/chat/completions · GET /v1/models |
| Base URL | https://api.apiiasenzacensura.com/v1 |
| Model ID | uncensored |
| API key | Authorization: Bearer YOUR_KEY |
| Other parameters | temperature, top_p, stop, seed, presence_penalty, frequency_penalty |
| Streaming | Yes — server-sent events; the last chunk carries token usage |
| Completion length | up to the rest of the 100,000-token window; max_tokens optional (no separate cap) |
| Tools / tool calls | Yes — tools, tool_choice; replies carry tool_calls, also when streaming; send results back as role: tool |
| Structured output | JSON object mode via response_format json_object |
| Context window | 100,000 tokens (prompt + completion together) |
| Response headers | X-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency |
| Max body | up to 8 MB per request |
| Parallel requests | up to 8 in parallel per key |
| Requests per minute | 300 requests per minute per key |
| Payment | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Token prices | input $0.25 / 1M tokens, output $1.00 / 1M tokens |
| Volume bonus | +5% from $50, +10% from $100 |
| Trial credit | $0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up |
| How you pay | prepaid credit, charged by real token usage; errors and refusals are free |
| Credit expiry | no monthly fee; paid credit does not expire |
| Account | Google or e-mail and password |
| Content policy | adult content allowed; sexual content involving minors is refused |
| Keys | one key per account, regenerate any time (the old one stops working) |
Errors and what to do
Errors come back as JSON with a stable type; failed and refused requests are not billed.
| HTTP | Type | What to do |
|---|---|---|
400 | bad_request | invalid JSON, empty messages, bad parameter, or prompt + max_tokens over the window — fix and resend |
401 | missing_key · invalid_key · key_revoked | check the Authorization header or use your current key |
402 | no_credit | balance is empty — top up, requests resume at once |
403 | content_blocked | refused by the content policy |
404 | not_found | only /v1/chat/completions and /v1/models exist |
413 | request_too_large | request body larger than 8 MB |
429 | rate_limited · concurrency | slow down: rate or parallel limit reached |
503 | upstream_busy | model busy — retry in a few seconds |
Frequently asked questions
Do I need to enter a phone number to register?
No, registration requires only email and password. No phone number is needed or required for access or for the free trial credit.
What content is blocked?
The only strict limit is sexual content involving minors. Everything else, including controversial and adult themes, is allowed for lawful use.
Does the credit expire?
No, prepaid credit never expires. You can buy it anytime and use it when you want, with no fixed monthly costs.
Your key is one form away
Create an account, copy the key, edit the base URL. That's all the configuration.