GPT Unfiltered API Quickstart

Installation and Setup

Start by generating your API key on the dashboard. You can sign in with Google or use an email and password, and the key displays immediately. Use the official SDKs for any language; they require only the base URL and your key. This works with any OpenAI-compatible client because we follow the standard interface.

• Base URL: https://api.gptunfiltered.cc/v1
• Model ID: uncensored
• Auth: Bearer token via API key

Sending Your First Request

Send a simple text completion to test the connection. Use the POST method on the chat completions endpoint with your model ID. The response returns plain text without any content refusals for lawful adult use.

Here is the standard cURL command to verify your setup.

Copycurl https://api.gptunfiltered.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all python standard library modules"}]
  }'

The response includes the generated text and token usage statistics. You can now integrate this into your application logic.

Streaming Responses

Enable streaming to receive tokens in real-time. Set the stream parameter to true in your request body. The API returns Server-Sent Events (SSE) for low-latency output.

Use this Python snippet to handle the stream efficiently.

Copyfrom openai import OpenAI

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

Each chunk contains partial text and usage data. Collect the chunks to reconstruct the full response. This approach reduces perceived latency for end-users.

Function Calling Support

Pass tools to the model for structured actions. Define your function schema in the tools array. The model returns tool calls when appropriate.

Here is how to configure function calling in Node.js.

Copyimport OpenAI from "openai";

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

Process the tool calls in your application code. Execute the function and send the result back to the model if needed. This enables complex workflows without manual parsing.

JSON Mode

Force the output into strict JSON format. Set the response_format parameter to json_object. This ensures the model returns valid JSON without markdown wrappers.

Use this configuration for reliable parsing in your backend.

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)

The response contains only the JSON object. Handle parsing errors gracefully in case of edge cases. This mode is ideal for API integrations requiring structured data.

Rate Limits and Costs

Monitor your usage to avoid service interruptions. The limit is 300 requests per minute per key. You can have 8 concurrent requests at any time. The request body size is capped at 8 MB.

Pricing is transparent and per-token. Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors and refusals are free. Use prepaid credit with no expiration. Upgrade your top-up for bonus credits.

Parameters and Settings

Adjust model behavior with standard parameters. Use temperature to control randomness. Set top_p for nucleus sampling. Define stop sequences to halt generation early.

You can also set the seed for reproducible outputs. Adjust presence_penalty and frequency_penalty to influence token repetition. These settings allow fine-tuning the model's style and accuracy.

Context Window and Constraints

The model supports a 100,000-token context window. This includes both the prompt and the completion. Max output is 16,000 tokens per request. If you do not set max_tokens, the default is 2,048 tokens.

This large window allows for extensive document processing. You can pass long conversations or large codebases. Monitor your token usage to stay within limits.