Uncensored Text API
Get an Uncensored LLM API Key
Use a single text endpoint for draft revision and conversational applications. Supply the source material and the changes you want, then compare the returned draft with the original before using it.
- OpenAI-compatible chat completions
- 100k context window
- No monthly fees or subscriptions
Try it in one request
curl https://api.uncensoredapis.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.uncensoredapis.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.uncensoredapis.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);- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
What you get
OpenAI Compatible
Works with official OpenAI SDKs and clients by simply changing the base URL and API key. Supports streaming and tool calling.
One model endpoint
Use one public model ID without choosing a provider on each request. Check behavior with saved inputs before integrating it.
Transparent Pricing
Pay-as-you-go prepaid credits with no monthly fees. Input tokens cost $0.15 per 1M, output tokens $0.50 per 1M.
Privacy First
Prompts are not used for training. An account needs only an email and password, with no phone number or card required for trials.
High Volume Ready
Supports 300 requests per minute per key with an 8 MB request body limit. Regenerate your API key instantly if needed.
Review content
Define the task’s boundaries and check the returned text. Handle refusals in the application; sexual content involving minors is prohibited.
How it works
Get Your Key
Sign up with an email and password to receive your API key immediately.
Add Credits
Top up by crypto (USDT on TRC20, USDC on Base); start with $20 or claim your $0.50 trial credit.
Start Generating
Point your OpenAI-compatible client to our base URL and send chat completion requests.
What people build with it
Fiction drafts
Provide a scene brief with adult fictional characters and content boundaries. Review the generated draft against that brief before use.
Data Labeling
Label or classify data where the model might otherwise refuse to process certain tags or categories. Process raw data without soft restrictions.
Chatbot development
Send the recent dialogue and a character description. Check the next reply for continuity and handle incomplete or refused requests.
Security Research
Test model outputs for edge cases and refusal behaviors in a controlled environment. Analyze how uncensored models handle controversial prompts.
Why Choose Our Uncensored API?
This service supplies one independent text model through Chat Completions. It is not GPT, Claude, Gemini or Grok. A single endpoint simplifies model selection but does not establish consistent output or privacy. Check your application’s saved requests and the service’s data-handling terms.
OpenAI-Compatible & Easy to Integrate
Our API follows the OpenAI chat-completions standard, making integration straightforward. Use the official OpenAI SDKs or any compatible client by changing the base URL to https://api.uncensoredapis.com/v1 and providing your API key. We support streaming via Server-Sent Events (SSE) and tool/function calling. The model ID is simply "uncensored". We do not offer embeddings, image, audio, or video generation, nor fine-tuning. It is strictly a text in, text out service.
- POST /v1/chat/completions for generation
- GET /v1/models for model info
- 100,000 token context window
Text generation with explicit boundaries
Try a bounded text task: provide three dialogue lines, name the characters and request two shorter versions. Compare each version with the source for changed names, events or meaning. Keep content review and refusal handling in your application.
Simple Pay-As-You-Go Pricing
Input costs $0.15 per million tokens; output costs $0.50 per million. Paid top-ups range from $20 to $500 and paid credit does not expire. Bonuses are 5% from $50, 10% from $100 and 15% from $200. Eligible new accounts can request a $0.50 trial for 7 days; verification and processing may be required.
Questions and answers
Is this API compatible with the official OpenAI SDK?
Yes. It supports the standard chat-completions endpoint. You only need to update the base URL to our endpoint and provide your API key. Streaming and tool calling are supported.
What is the context window size?
The model supports a 100,000 token context window, covering both prompt and completion tokens. This allows for processing long documents or extended conversations.
Do you offer image or audio generation?
No. This is a text-only API. We do not offer embeddings, image, audio, or video generation. We also do not offer fine-tuning services.
What content is blocked?
The only hard content limit is sexual content involving minors. All other lawful adult, fictional, or controversial topics are generated without refusal.
Is this API for you if you need an SLA guarantee?
No. We do not offer SLA percentages, SOC2/HIPAA/ISO certifications, or on-prem deployment. It is not for you if you need those specific enterprise guarantees.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Example: revise dialogue without changing the facts
Give the model three fictional dialogue lines and a glossary containing the names Mira, Oren and Port Seven. Ask for a concise version and a more conversational version, each with an unchanged glossary. Return JSON with concise, conversational and changed_facts fields. Check both versions against the source and reject added events or altered names. The example tests an editing workflow; it does not establish that every generated rewrite preserves meaning.
Guides
Practical articles on setup, pricing and integration.
OpenAI-Compatible API Tester: Verify Any EndpointBuild an openai compatible api tester with curl and Python: check /v1/models, a minimal chat call, streaming and error handling before you trust…
LLM API Free Trial: What to Test in the First HourGot trial credit for an LLM API? Use this checklist to test the key, streaming, tool calls, JSON mode and rate limits, and see how far $0.50…
Excessive Agency in LLM Agents: Safe Tool CallingHow attackers abuse agents that hold too many tools or permissions, and the design patterns that limit the damage when you give a model tool calling.
Agents on an Uncensored LLM API: Tool Calling, Frameworks and GuardrailsBuild agents with our uncensored LLM API. Supports function calling, 100k context, and OpenAI compatibility. Start building now.
Errors and Rate Limits: A Practical Playbook for the Uncensored APIMaster uncensored LLM API error handling with retry rules, 300 requests/minute limits, and 402 flows. Start optimizing your integration now.
Uncensored API Reference, Explained Field by FieldUncensored API reference for OpenAI-compatible requests. See fields, streaming, usage, and function calling examples. Get your API key now.