Uncensored chat API for your text pipeline
uncensored LLM API for media pipelines
A hosted, OpenAI-compatible chat-completions API serving a single, high-context, refusal-free model. Get the text brain for your audio, video, and image pipelines without content filters blocking your creative control.
- OpenAI-compatible chat endpoint
- 100k context window for long scripts
- No subscription, pay-as-you-go
Try it in one request
curl 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."}]
}'from 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)import 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);What you get
One Uncensored Model
We run one open-weight model tuned to answer without refusals for lawful adult, fictional, or controversial topics. It is not GPT, Claude, Gemini, or any other vendor's model.
Standard Endpoints
Use POST /v1/chat/completions with streaming via SSE and tool/function calling support. It works with official OpenAI SDKs by changing the base URL and API key.
100k Context Window
Process up to 100,000 tokens of prompt and completion data. Ideal for long-form scripts, detailed context injection, and complex post-processing tasks.
Transparent Pricing
Pay-as-you-go prepaid credit. $0.15 per 1M input tokens and $0.50 per 1M output tokens. No monthly fees or subscription lock-in.
Privacy Focused
Prompts are not used for training. An account requires only an email and password. Sign up instantly without a phone number or credit card for the trial.
Simple Limits
300 requests per minute per key with an 8 MB request body limit. One key per account, easily regenerated to revoke access if needed.
How it works
Create Account
Sign up with email and password to receive your API key immediately.
Configure SDK
Update your client's base URL to https://api.fluxapikey.com/v1 and set your key.
Send Requests
Send text prompts to the uncensored model and receive direct text outputs.
What people build with it
Script Writing for Video
Generate dialogue and narrative scripts without filters blocking creative or mature themes. Perfect for autonomous video generation pipelines needing consistent tone.
Audio Captioning
Process long audio transcripts into summaries or metadata without context loss. Handle nuanced language that standard models might over-sanitize or refuse.
Image Prompt Engineering
Create detailed, uncensored prompts for image generation models. Avoid refusals when generating specific artistic styles or mature subjects for creative projects.
Data Extraction
Extract structured data from unstructured text with high context retention. Ideal for post-processing raw text outputs from other AI pipelines.
Why Uncensored Matters for Media Pipelines
When building AI media pipelines, content filters often break automation. Standard models refuse mature themes, specific artistic styles, or nuanced narratives, causing your script or caption generation to fail or return bland text. Our flux api serves a single, uncensored large language model optimized for creative control. It does not refuse lawful adult, fictional, or controversial topics, ensuring your pipeline stays on track.
This is not a general-purpose assistant. We do not generate images, audio, or video. We provide the text brain behind your media. Whether you are writing scripts for AI video or generating prompts for image models, you need a model that answers your prompt without unnecessary restrictions. Our model is open-weight and tuned specifically for this reliability.
OpenAI-Compatible Endpoints: Stream & Tools
Integrate our API using standard tools. We support POST /v1/chat/completions with streaming via Server-Sent Events (SSE) and full tool/function calling. This means you can use the official OpenAI SDKs or any OpenAI-compatible client library. Just change the base URL to https://api.fluxapikey.com/v1 and provide your API key.
curl 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 compatibility reduces development time. You do not need to learn a new protocol. The model id to send is "uncensored". It is an open-weight model run on our own GPU servers, distinct from GPT, Claude, Gemini, Grok, or DeepSeek. It handles text in and text out, supporting the complex context requirements of media pipelines.
100k Context Window for Long-Form Scripts
Standard context windows often truncate long scripts or detailed instructions. Our API supports a 100,000-token context window for both prompt and completion. This allows you to inject extensive style guides, character sheets, or previous context into a single request.
For video or audio pipelines, this means you can maintain narrative consistency over longer durations. You do not need to split prompts and hope the model remembers earlier details. The entire context is processed in one request, reducing latency and complexity. This is critical for post-processing tasks where the model must reference large blocks of source text accurately.
Pay-As-You-Go Pricing: No Subscription Lock-in
We do not charge monthly fees. You pay only for what you use. Input tokens cost $0.15 per 1 million tokens, and output tokens cost $0.50 per 1 million tokens. Top-ups start at $20 by crypto (USDT on TRC20, USDC on Base). You also receive bonus credit: +5% from $50, +10% from $100, and +15% from $200.
Paid credit never expires, so you can use it when your pipeline needs it. New users get $0.50 of trial credit, one per person, valid for 7 days, no card needed. This model is ideal for variable workloads. Claim this credit with one click on your API key page. If your media pipeline scales up or down, your costs follow exactly. There is no commitment to a subscription tier.
Questions and answers
Is this model GPT-4 or another vendor model?
No. The model is an open-weight model run on our own GPU servers. It is not GPT, Claude, Gemini, Grok, DeepSeek, or any other vendor's model. It is specifically tuned to answer without content refusals for lawful adult use.
What content is blocked?
We have one hard content limit that always applies: no sexual content involving minors. Requests of that kind are blocked. Other adult, fictional, or controversial topics are generally not refused.
Do you use my prompts for training?
No. Your prompts are not used for training. We value privacy, especially for creative pipelines. An account requires only an email and a password, with no phone number or credit card needed for the trial.
Can I generate images or video with this API?
No. This is a text chat-completions API. We do not generate audio, images, or video. We provide the text output for your media pipelines, such as scripts, captions, or prompts for other models.
What are the rate limits?
You are limited to 300 requests per minute per key, with an 8 MB request body limit. You get one key per account, which can be regenerated at any time to revoke the old one.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Guides
Practical articles on setup, pricing and integration.
Flux API Key: What It Is and Where a Text API FitsPlain explanation of the Flux key people search for, why an image key will not call a chat model, and how a separate text-only LLM API key helps…
LLM API for Flux Prompts: A Practical WorkflowSet up a hosted text LLM to write and expand image prompts: system prompt, sampling settings, JSON batches, context use, limits and exact…
How to Implement an LLM in Python With a Hosted APIStep-by-step Python code for using a hosted OpenAI-compatible LLM: first call, streaming, chat history, JSON mode, tool calling, retries and cost…
Runway API: The Ultimate Guide to Text-to-Video WorkflowsA production checklist for using AI APIs with Runway. Learn how to integrate uncensored text models for prompt generation, script writing, and