Uncensored AI API Quickstart

Installation and Configuration

Initialize your client with the base URL and your API key. Our service uses standard authentication headers compatible with the official SDKs. Pass your key as the Bearer token in the Authorization header. This allows you to switch providers without rewriting your application logic.

Copycurl https://api.uncensoredgptchat.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize the technical documentation for the new API endpoint"}]
  }'

You can generate a key instantly by signing up with Google or email. No phone number is required for the trial credit.

Basic Chat Completion

Send a simple text request to get a direct response. Use the chat/completions endpoint with the model ID uncensored. The system returns generated text based on your prompt without filtering lawful adult content.

Copyfrom openai import OpenAI

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

This approach works for generating creative writing, roleplay, or answering questions that standard models might refuse. You control the context by defining the user and assistant messages clearly.

Streaming Responses

Receive tokens in real-time using Server-Sent Events. This reduces perceived latency for long outputs. The SDK handles the stream and yields tokens as they are generated.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredgptchat.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 is ideal for chat interfaces where users expect immediate feedback. You can process each token as it arrives without waiting for the full completion.

Function Calling (Tools)

Define external tools and let the model decide when to use them. Pass a list of function definitions in the tools parameter. The API returns structured tool calls that your code can execute.

This feature supports standard function calling formats. You can integrate custom logic for data retrieval or action execution seamlessly.

JSON Mode

Force the output into a strict JSON object. Set response_format to {"type": "json_object"}. This ensures the response is parseable by your application.

Use JSON mode when you need structured data for downstream processing. The model adheres to the schema you provide in the prompt.

Parameters and Limits

Manage concurrency and token usage with specific limits. You can send 300 requests per minute and 8 concurrent requests per key. The context window supports 100,000 tokens total.

Errors like 401 indicate an invalid key, while 402 means no credit remains. Rate limits return 429. Adjust temperature and top_p to control randomness. Errors and refusals do not consume credit.

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)