Quickstart: Uncensored Text API for Image Pipelines

Base URL & Authentication

Our API follows the standard OpenAI chat-completions structure. To begin, navigate to the Get API key page and sign up with an email and password. The API key is displayed immediately. No phone number or credit card is required for the trial, though prepaid credit is needed for sustained usage.

Set your base URL to https://api.imagegenapi.com/v1. Include your API key in the Authorization header as a Bearer token. This setup works with any OpenAI-compatible client library. The model identifier to use is uncensored, an open-weight model tuned to answer without refusals for lawful adult use.

Sending a Prompt

Send a standard chat.completions request to generate text. The API accepts a list of messages in the messages array. It returns a JSON object containing the completion. This is ideal for one-off prompt generation or metadata editing tasks where streaming is not required.

Copycurl https://api.imagegenapi.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 request body includes the model field set to uncensored and your conversation history. The response contains the assistant's reply, which you can then feed into your image generation pipeline or use as a caption.

Python SDK Integration

For Python developers, use the official openai library. Configure the base_url and api_key to point to our service. This allows you to leverage familiar Python idioms while accessing our uncensored model.

Copyfrom openai import OpenAI

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

Initialize the client with your key and the correct base URL. Call chat.completions.create() with your messages. This approach is best for batch processing or when you need to parse the JSON response directly in your application logic. Remember that the model ID must be uncensored.

Node.js SDK Usage

Node.js developers can use the openai npm package. Set the baseURL to our endpoint. This is useful for server-side rendering or API gateways where you need to process text responses asynchronously.

Copyimport OpenAI from "openai";

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

Create the client instance with your API key and base URL. Invoke chat.completions.create() to get the text output. This method is suitable for generating scripts, captions, or extracting information from text before it is used in your image pipeline.

Streaming Responses

For real-time text generation, enable streaming by setting stream: true. The API returns a Server-Sent Events (SSE) stream, not a single JSON object. You must handle the delta chunks as they arrive to reconstruct the full message.

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)

Iterate over the stream to display text incrementally. This is critical for applications where latency matters, such as live prompt editing or interactive chat interfaces. Each chunk contains a portion of the response, allowing you to render text as it is generated.

Rate Limits & Constraints

Each API key is limited to 300 requests per minute. The request body must not exceed 8 MB. If you exceed the limit, you will receive a 429 error. Regenerate your key if needed, which revokes the old one.

If your prepaid credit is exhausted, the API will reject requests. There is no free unlimited tier; you must top up with credit. The 401 error indicates an invalid or missing API key. Ensure your key is correctly set in the authorization header. The context window is 100,000 tokens for prompt plus completion.