Quickstart for GPT 5 users

Authentication: Using Your API Key

To begin, you need an API key from your account dashboard. The gpt 5 api uses standard bearer token authentication. Include your key in the Authorization header as Bearer YOUR_API_KEY. This key grants access to the single uncensored model via the base URL https://api.gpt5apikey.com/v1. If you lose your key, you can regenerate it at any time, which immediately invalidates the previous one. There is no need to link a credit card for the initial trial credit, which provides $0.50 valid for 7 days.

Endpoint: POST /v1/chat/completions

Send your prompt to the chat completions endpoint. The API accepts standard OpenAI JSON payloads. Ensure you set the model field to uncensored. The system expects a messages array containing your conversation history. This endpoint supports both synchronous and asynchronous requests, making it easy to integrate into existing workflows without changing your client library.

Copycurl https://api.gpt5apikey.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."}]
  }'

The response returns a JSON object containing the generated text, token usage statistics, and finish reasons. This structure mirrors the standard OpenAI response format, allowing you to use any compatible SDK or HTTP client without custom parsing logic.

Python SDK Integration

Using the official Python SDK is straightforward. Set the base_url to our endpoint and provide your API key. The library handles serialization and error handling automatically. You can pass your entire conversation history as a list of message dictionaries. The API processes the input and returns the model's completion.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.gpt5apikey.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 identically for simple prompts and multi-turn conversations. The SDK manages the HTTP connection pool efficiently, ensuring minimal latency for subsequent requests. You can also pass additional parameters like temperature or max_tokens to control the output behavior.

Node SDK Integration

For JavaScript developers, the Node SDK follows the same pattern. Initialize the client with your base URL and key. The API supports standard tool definitions, allowing you to define functions that the model can call. This is useful for generating structured data or triggering external actions based on user input.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.gpt5apikey.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 Node environment handles asynchronous operations naturally. You can chain requests or run them in parallel depending on your application's needs. The SDK provides type definitions if you are using TypeScript, ensuring better developer experience during development.

Support for Streaming Responses

Enable streaming by setting stream: true in your request. The API returns a Server-Sent Events (SSE) stream. Each chunk contains a partial response, allowing you to display text to the user as it is generated. This improves perceived latency, especially for long responses. The streaming response includes token usage data in the final chunk.

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)

Handle the stream by reading chunks until the response ends. Error handling is crucial; if the connection drops, you may need to retry or handle the partial output. The streaming format is compatible with most modern HTTP clients and SDKs that support SSE.

Rate Limits, Errors, and Context

Each API key is limited to 300 requests per minute. If you exceed this, you will receive a 429 status code. The request body must not exceed 8 MB. Authentication errors return a 401 status if the key is invalid or expired. If your prepaid credit is exhausted, you receive a 402 status. The model supports a context window of 100,000 tokens, including both input and output. Plan your prompt size accordingly to avoid truncation. The model does not refuse lawful adult or controversial topics, providing a true uncensored experience.