Direct Control
One public model ID keeps provider selection out of the request. Test your saved prompts when integrating the service: outputs and response times can still vary.
Uncensored AI API
Connect a text application to one Chat Completions model. Start with a saved dialogue prompt, inspect the returned message, and test streaming or tool calls separately before adding the endpoint to a production workflow.
curl https://api.uncensoredaiapis.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.uncensoredaiapis.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.uncensoredaiapis.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);One public model ID keeps provider selection out of the request. Test your saved prompts when integrating the service: outputs and response times can still vary.
Use the model within the service’s content rules. Validate returned text and handle refusals or unsuitable replies in the application.
Pay only for what you use with paid credit that does not expire. No monthly fees, no subscriptions, and no hidden costs. Trial credit has a separate 7-day validity period.
Works with the official OpenAI SDKs and any OpenAI-compatible client by simply updating your base_url and API key.
Sign up with just an email and password. Your prompts are not used for training, and you can regenerate your API key instantly.
Get $0.50 in trial credit after sign-up with no card required, allowing you to test the API before committing to credit. Claim this credit with one click on your API key page.
Create an account with your email and password to receive your API key immediately.
Update your OpenAI-compatible client with the provided base_url and API key.
Start sending text in and getting text out via the standard chat-completions endpoint.
For an adult-fiction application, send a scene brief with clearly adult fictional characters and explicit boundaries. Review the returned draft before displaying it.
Provide a character sheet and the recent dialogue. Check the returned line against names, events and the intended voice; do not assume the model preserves every detail.
Use synthetic inputs to test how your application handles difficult or unexpected model replies. Record the prompt, output and validation result so that the test can be repeated.
Use synthetic prompts to draft test material, then review and label each result before adding it to a dataset. Check the terms that apply to the intended downstream use.
This service exposes one text model through Chat Completions. It does not offer embeddings, image, audio or video generation, or a choice of vendor models. Test your application’s prompts, error handling and token costs before moving traffic. Read the applicable data-handling terms before sending sensitive material; a single endpoint does not establish confidentiality.
Our API follows the OpenAI chat-completions standard. You can use the official OpenAI SDKs or any compatible client by changing the base_url to https://api.uncensoredaiapis.com/v1 and setting your API key. The endpoint POST /v1/chat/completions supports streaming via SSE and tool/function calling. The model ID to send is "uncensored". We do not offer embeddings, images, audio, or video. This simplicity allows you to drop our API into existing projects with minimal code changes. It is a direct text-in, text-out interface designed for developers who need reliability.
We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no monthly fees or subscriptions. You pay for what you use with paid credit that does not expire. You can top up from $20 using crypto (USDT on TRC20, USDC on Base). We offer a +5% bonus credit for purchases of $50, a +10% bonus for $100, and a +15% bonus for $200 or more. New users get $0.50 in trial credit valid for 7 days, one per person, with no card required. This transparent pricing model ensures you know exactly what you will pay for your API usage. Claim this credit with one click on your API key page.
Use this endpoint when your application sends text and needs text back. It does not generate images, audio or video, produce embeddings, fine-tune models or route between providers. It also does not serve GPT or Claude. If your project requires a named vendor model, an on-premises installation, a contractual SLA or a compliance certification, check those requirements before choosing this service.
Use a Chat Completions client with base URL https://api.uncensoredaiapis.com/v1, the current key and model uncensored. Test the methods, parameters and streaming behavior your application needs; support for every OpenAI endpoint is not implied.
Sexual content involving minors is prohibited. For other subjects, responses remain subject to model behavior and applicable service rules. Your application should handle refusals and review generated content.
No, we do not offer embeddings, images, audio, or video. We provide a text-only API for chat-completions. If you need multimodal capabilities, you will need to use a different provider or combine APIs.
Eligible accounts can request a $0.50 trial for 7 days. Verification and processing may be required. Check the account balance before sending a test request.
No, your prompts are not used for training. We value privacy and do not use your data to improve our models. Your account only requires an email and password.
Create an account, copy the key, change the base URL. That is the whole setup.
For a fictional dialogue test, send a character brief and three preceding lines. Request one reply under 60 words and a JSON object with speaker, line and continuity_flags fields. Parse the object, count the words and compare names and events with the supplied brief. Reject invented character details before displaying the line. This is an illustrative test setup; review the generated answer rather than assuming it will pass.
Practical articles on setup, pricing and integration.
AI API Free Tier: What Developers Should ExpectWhat an ai api free tier usually means, where the limits bite, and how a one-click $0.50 trial plus pay-per-token credit compares for prototyping…
How to Use an OpenAI-Compatible API in 5 StepsLearn how to use openai api style endpoints: get a key, set the base URL, call chat completions, stream, force JSON and use tools with the…
Migrate from OpenAI or OpenRouter to an uncensored AI APIGet your uncensored AI API key. OpenAI compatible API with pay per token pricing. Test function calling now.
Uncensored AI API use cases for developersExplore uncensored AI API key use cases for roleplay, fiction, and agents. OpenAI compatible API key with AI sdk function calling. See costs per…
Uncensored AI API free trial and FAQGet an uncensored AI API key with $0.50 credit for 7 days. See what tokens it buys and check billing FAQ. Start now.