Developer Documentation for the gapgpt api

Base URL and Authentication

The gapgpt API uses the standard OpenAI-compatible endpoint structure. Point your client to https://api.gapgptapi.com/v1 and supply your API key in the Authorization header. The system requires a valid key for every request. You generate this key instantly via the dashboard using Google or email credentials.

Quickstart: First Request with cURL

Send your first prompt to the uncensored model using any HTTP client. This example requests a JSON response to ensure structured output for your application logic.

Copycurl https://api.gapgptapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list the top five python libraries for async web scraping"}]
  }'

Replace YOUR_API_KEY with your actual credential. The endpoint accepts the standard model parameter set to uncensored. You receive a text response immediately.

Integrate with Python

Use the official openai Python package to interact with the API. You must override the base URL to point to our servers. This allows you to use familiar SDK methods without changing your code structure significantly.

Copyfrom openai import OpenAI

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

Set the model to uncensored. The SDK handles the streaming and parsing automatically. Ensure you have the latest version of the package installed.

Integrate with Node.js

Initialize the client with the correct base URL. This ensures your Node.js application routes requests to our uncensored model instead of OpenAI. The rest of the code mirrors standard OpenAI patterns.

Copyimport OpenAI from "openai";

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

Pass the uncensored model ID. This approach works with both CommonJS and ES module setups. You can start sending prompts immediately.

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns a Server-Sent Events stream. Each chunk contains partial text and token usage data. This reduces perceived latency for large responses.

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 final chunk includes the total token count for the request. You can process tokens in real-time or buffer them for later use. This method works well for chat interfaces.

Error Handling and Limits

Monitor HTTP status codes to handle errors gracefully. A 401 error means your API key is invalid or missing. A 402 error indicates insufficient prepaid credit. A 429 error signals that you have exceeded the 300 requests per minute limit.

The context window supports 100,000 tokens total. You can request up to 16,000 tokens of output. If you do not specify max_tokens, the default is 2,048 tokens. Implement exponential backoff for rate limits. Your credit never expires, so you can retry later.