OpenAI-compatible uncensored API
uncensored API explained, and a compatible alternative
A single, dedicated large language model for unrestricted text generation via the standard OpenAI-compatible endpoint. No model routing, no extra services, just high-performance text.
- OpenAI-compatible endpoint
- 100k token context window
- Pay-as-you-go pricing
- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Try it in one request
https://api.uncensoredgptapi.com/v1uncensored
curl https://api.uncensoredgptapi.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.uncensoredgptapi.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.uncensoredgptapi.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
Drop-in Compatibility
Use the standard /v1/chat/completions endpoint. It works with the official OpenAI SDKs and any compatible client by simply changing the base_url and API key.
Dedicated Model
We serve one uncensored large language model tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model.
Streaming Support
Generate responses in real-time using Server-Sent Events (SSE). This allows for instant token streaming in your application without waiting for the full response.
Function Calling
Integrate with tools and functions seamlessly. The API supports structured outputs and tool use, making it suitable for complex agent workflows.
Generous Context
Each request supports up to 100,000 tokens for the combined prompt and completion. This allows for long documents and extensive conversation history.
Simple Limits
Get 300 requests per minute per key with an 8 MB request body limit. Keys can be regenerated instantly to revoke access if needed.
How it works
Sign Up
Create an account with just an email and password to receive your API key immediately.
Configure Client
Update your SDK configuration to point to our base URL and insert your new API key.
Send Request
Make a POST request to /v1/chat/completions with the model ID 'uncensored' and your messages.
What people build with it
NSFW Content Generation
Ideal for creative writing and roleplay applications that require unrestricted adult content without standard model refusals. It handles mature themes directly without extra prompting.
Large Context Analysis
Process long documents up to 100k tokens for summarization or extraction tasks. The dedicated model handles extended contexts efficiently without unnecessary routing delays.
Agent Tool Use
Build autonomous agents that can call functions and tools reliably. The API supports tool definitions and structured outputs for complex decision-making loops.
Beta Testing Workflows
Test your application's integration with an OpenAI-compatible endpoint before scaling. The prepaid credit model lets you pay only for what you use during development.
Why Choose Our Uncensored GPT API?
Most API aggregators bundle image, video, and multiple vendors, adding complexity and latency. We focus purely on high-performance, unrestricted text generation. This uncensored gpt api serves a single, dedicated model run on our own GPU servers. It is an open-weight model tuned to answer without content refusals for lawful adult use. You get direct access to the model without the overhead of routing logic. The API is OpenAI-compatible, meaning you can swap it into existing projects with minimal code changes. It supports streaming and function calling, making it suitable for both chat interfaces and complex agent workflows. There is no model choice to manage, just a reliable endpoint for text generation.
OpenAI Compatible Endpoint
Our API follows the standard OpenAI chat-completions format. You can use the official OpenAI SDKs or any compatible client by simply changing the base_url to https://api.uncensoredgptapi.com/v1 and providing your API key. The model ID to send is "uncensored". This ensures maximum compatibility with existing tools and SDKs without the complexity of model routing. We do not offer embeddings, image, audio, or video generation, nor do we support fine-tuning. It is a text-in, text-out service. Streaming via Server-Sent Events (SSE) is supported for real-time token delivery. Function calling is also available for structured outputs and tool use. This simplicity reduces integration time and debugging overhead for developers who need a straightforward text generation endpoint.
Unrestricted Content Generation
The model is designed to handle NSFW topics, controversial subjects, and creative fiction without the standard content filters found in mainstream models. It does not refuse lawful adult, fictional, or security-research topics. The only hard content limit that always applies is the prohibition of sexual content involving minors; requests of that kind are blocked. This makes the uncensored ai api ideal for applications requiring mature content or unrestricted creative freedom. Prompts are not used for training your data, ensuring privacy for your inputs. The model runs on our own infrastructure, providing consistent performance. It is not GPT, Claude, or any other vendor's model, but a dedicated open-weight model optimized for this specific use case.
Developer-Friendly Pricing
We offer transparent, pay-as-you-go pricing with no monthly fees. The cost is $0.15 per 1M input tokens and $0.50 per 1M output tokens. You can top up from $20 by crypto only (USDT on TRC20, USDC on Base). Bonus credits are available: +5% for deposits of $50 or more, +10% for deposits of $100 or more, and +15% for deposits of $200 or more. Paid credit never expires, so you can use it whenever you need it. New users get $0.50 of trial credit, one per person, valid for 7 days, requiring no card. This low barrier to entry allows you to test the uncensored llm api with zero financial risk. Claim this credit with one click on your API key page. There are no hidden fees or subscription traps. You pay only for the tokens you consume, making it cost-effective for both small projects and high-volume applications.
Simple Integration
Getting started requires only an email and a password. Sign up on the "Get API key" page to receive your key immediately. No phone number or credit card is needed for the trial. The API key is shown once after signup and can be regenerated at any time, revoking the old one. You can use up to 300 requests per minute per key, with an 8 MB request body limit. This is sufficient for most development and production use cases. The uncensored api integrates easily into existing workflows that already use OpenAI-compatible endpoints. You do not need to learn a new protocol or format. Just update your base URL and model ID, and your code will work as expected.
No Hidden Fees
Our pricing is straightforward. You pay for input and output tokens based on the rates listed. There are no connection fees, no per-request charges, and no minimum commitments. The trial credit gives you $0.50 to test the api nsfw capabilities without adding a payment method. Claim this credit with one click on your API key page. Bonus credits add value to your deposits without complicating the billing structure. Credit does not expire, so you can top up occasionally without worrying about losing funds. This model is not for enterprises needing SLAs, SOC2 certifications, or on-prem deployment. It is for developers who want a reliable, uncensored text API without the complexity of large aggregators. If you need embeddings, image generation, or model routing, this dedicated text endpoint is the right choice for your text generation needs.
Questions and answers
Is this the official OpenAI API?
No, this is an independent service. We serve a dedicated open-weight model that is compatible with the OpenAI chat-completions endpoint format. It is not GPT or any other vendor's model. You can use the OpenAI SDKs by changing the base URL and model ID.
Does the uncensored gpt api support streaming?
Yes, streaming via Server-Sent Events (SSE) is fully supported. You can set the stream parameter to true in your request to receive tokens in real-time. This is useful for chat interfaces and applications that display text as it is generated.
What is the context window size?
The context window is 100,000 tokens. This includes both the prompt and the completion. You can send long documents or maintain extensive conversation histories within this limit. Requests exceeding this limit may be rejected or truncated depending on the implementation.
Can I use this for NSFW content?
Yes, the model is tuned to answer without content refusals for lawful adult use. It handles NSFW topics freely. The only hard limit is that sexual content involving minors is blocked. This uncensored api is ideal for creative writing, roleplay, and other applications requiring unrestricted content.
Do I need a credit card to start?
No, you can sign up with just an email and password. New users get $0.50 of trial credit, one per person, valid for 7 days. Claim this credit with one click on your API key page. No card is required to start testing. You can add credits by crypto (USDT or USDC) later to top up your balance for continued use.
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.
ChatGPT API Cost per Month: Example WorkloadsEstimate your chatgpt api cost per month with four example workloads, exact token math, and the same loads priced at $0.15 and $0.50 per 1M tokens.
Free Chat GPT API Alternatives and Their Real LimitsCompare free chat gpt api alternatives by their real limits: trial credits, local models and hosted tiers, and when a $0.15/$0.50 per 1M token API…
GPT Model API Pricing: Per-Token Costs, Worked ExamplesHow gpt model api pricing works, with exact costs for our API at $0.15 and $0.50 per 1M tokens, monthly estimates, and ways to keep your bill low.
GPT API base_url: How to Set It for Any OpenAI ClientSet the gpt api base_url in Python, Node, curl or an env var to point OpenAI-compatible code at a different endpoint, with fixes for the usual…
Chat GPT Roleplay Prompt: A Template and API SetupA reusable chat gpt roleplay prompt with a character sheet, scene rules and style notes, plus API code and settings for long, consistent stories.
Uncensored AI API: Common Mistakes and How to Fix ThemFix uncensored API integration errors with streaming, tool calling, and context windows. Learn how to resolve common issues with our uncensored…