Flux API: Prompts and scripts over one endpoint

Base URL and Authentication

Our API follows the standard OpenAI chat-completions structure. To begin, you need a base URL and an API key. The base URL for all requests is https://api.fluxapikey.com/v1. You can obtain an API key by signing up on the Get API key page with just an email and password. No credit card is required for the trial.

Pass your key in the Authorization header as a Bearer token. Each account is limited to one key at a time; regenerating it invalidates the previous one. Prompts are not used for training, and the only hard content limit is no sexual content involving minors.

Sending Your First Request

Make a POST request to /v1/chat/completions with your prompt. The model ID is always uncensored. This endpoint accepts standard JSON payloads and returns text responses. It supports streaming via Server-Sent Events (SSE) and tool/function calling.

Here is a basic example using curl:

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

This request sends your text to our GPU servers. The model is tuned to answer without refusals for lawful adult, fictional, or controversial topics. You can adjust the max_tokens and temperature parameters as needed.

Python SDK Integration

Use the official OpenAI Python SDK to interact with our API. Set the base URL to our endpoint and provide your API key. This allows you to use familiar methods like client.chat.completions.create.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.fluxapikey.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 setup ensures compatibility with existing codebases. The response object contains the generated text in response.choices[0].message.content. You can parse this text for scripts, captions, or metadata extraction in your video or audio workflows.

Node.js SDK Usage

For JavaScript environments, use the OpenAI Node.js SDK. Configure the baseURL and apiKey properties to point to our service. This enables seamless integration into Node.js applications for real-time text generation.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.fluxapikey.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 response structure matches the OpenAI format. You can access the generated content and handle errors using standard try-catch blocks. This approach is ideal for server-side processing in web applications or CLI tools.

Streaming Responses via SSE

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) with incremental chunks of text. This is useful for real-time applications where you want to display text as it is generated.

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)

Each chunk contains a partial response. You can accumulate these chunks to reconstruct the full text or display them in real-time. Streaming reduces the perceived latency for users waiting for long scripts or descriptions.

Limits, Errors, and Context Window

Our API has specific limits to ensure reliability. You can send up to 300 requests per minute per key. The maximum request body size is 8 MB. The context window supports 100,000 tokens for both prompt and completion combined.

Common errors include 401 for invalid keys, 402 for insufficient credit, and 429 for rate limits. If you exceed the rate limit, wait and retry. Our pricing is transparent: $0.25 per 1M input tokens and $1.00 per 1M output tokens. Prepaid credit never expires, and you can top up from $10.