EN ▾
Uncensored Chatbot APIDirect API access to one uncensored LLMGet API key

Uncensored Chatbot APISafety

No Code Chatbot Tutorial: Open WebUI and More

This no code chatbot tutorial gets you a working chat interface on an uncensored, OpenAI-compatible API without writing an app. You paste a base URL and a key into a tool that already has a chat window.

Updated

Modular blocks forming a chat window plugged into a server, representing a no-code chatbot setup

Key points

  • Any chat front end that accepts a custom OpenAI-compatible endpoint can use this API.
  • You need three values: the base URL, your key and the model ID uncensored.
  • Open WebUI and SillyTavern are two tools that support custom endpoints, and LangChain is the step up if you want a little code.
  • Start with the free trial, then top up from $20 with crypto.

What no code means here

You do not need to build a chat interface to talk to this model. Several open-source chat front ends were written to connect to any server that speaks the OpenAI chat format, and this API does. So a no code chatbot tutorial boils down to one idea: install a ready-made chat app, point it at a custom endpoint, and chat.

Be clear about the limit of that approach. These tools give you a private or team chat window. They are standalone apps, not widgets you drop into a web page. If you want a bot on your own site, you will need a backend, and the web chat tutorial covers that. Everything below is for people who want to chat, test personas or prototype with no programming.

What you need before you start

Gather three values.

  • Base URL: https://api.uncensoredchatbotapi.com/v1
  • API key: from the API key page. Sign up with Google or email and password, then claim the trial with one click. It gives $0.50 of credit, valid for 7 days, one per person, and needs no payment.
  • Model ID: uncensored

Authentication is a standard bearer token, which every OpenAI-compatible tool already handles. The endpoints are POST /v1/chat/completions for chat and GET /v1/models for the model list. Tools usually call the second one to fill their model dropdown, so if the list stays empty, the base URL is the likely culprit.

A quick sanity check from a terminal saves time:

curl https://api.uncensoredchatbotapi.com/v1/models \
  -H "Authorization: Bearer YOUR_KEY"

If that prints a model list, any tool you connect will work with the same values.

Option 1: Open WebUI

Open WebUI is a self-hosted chat interface that supports OpenAI-compatible connections. If you have Docker installed, one command starts it with your endpoint preconfigured:

docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL=https://api.uncensoredchatbotapi.com/v1 \
  -e OPENAI_API_KEY=YOUR_KEY \
  -v open-webui:/app/backend/data \
  --name open-webui \
  ghcr.io/open-webui/open-webui:main

Open http://localhost:3000, create the local admin account, and pick uncensored from the model dropdown. If you prefer to configure it in the interface, go to the admin settings, open the connections section, add an OpenAI connection and paste the base URL and key there. Menu names shift between versions, so check the project's own documentation if a label differs.

Set a system prompt per chat or per saved model preset, so your persona or house rules apply every time. Keep it short, since the system prompt is resent with each message and you pay for it as input tokens.

Option 2: SillyTavern for characters and roleplay

SillyTavern is a local front end built for character chat, with character profiles, lorebooks and group chats. It lets you add an OpenAI-compatible endpoint, which makes it a good fit for fiction and companion-style use by adults.

  1. Install SillyTavern following its own instructions and start it.
  2. Open the API connections panel and choose the chat completion type.
  3. Select the custom OpenAI-compatible source.
  4. Paste https://api.uncensoredchatbotapi.com/v1 as the endpoint and your key as the API key.
  5. Enter uncensored as the model ID, then press connect.

Once the status turns green, load or create a character and send a message. The 100,000-token context window means long character sheets and lorebooks fit, though a larger prompt costs more on every turn. For ideas on writing characters that stay consistent, read the guide to character and persona design. Keep stories to lawful adult use. Sexual content involving minors is never allowed.

Option 3: LangChain in five lines

If you can run one short Python script, LangChain gives you a bridge to templates, memory and agents later. It counts as low-code rather than no-code, but it takes almost no effort:

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="uncensored",
    base_url="https://api.uncensoredchatbotapi.com/v1",
    api_key="YOUR_KEY",
)
print(llm.invoke("Introduce yourself as a friendly guide in one sentence.").content)

Install it with pip install langchain-openai. From here you can add a prompt template, stream tokens or bind tools. Tool calling and JSON mode are both supported by the API, so agent-style chains work. Parameters like temperature, top_p, stop and seed are passed through, so you can tune creativity the same way as with the original OpenAI package.

Writing the system prompt without code

The system prompt is where a no-code setup gains or loses quality. Every tool above has a box for it, and the contents work the same in all of them. Aim for four short parts: the role, the voice, the format and the boundaries.

A role line says who the bot is, for example a travel planner for a small agency or a narrator for a mystery game. A voice line sets the register, such as warm and brief, or dry and formal. A format line fixes the length and shape of replies, like three short paragraphs or a bulleted plan. A boundary line states what the bot should decline or redirect, which matters for any public-facing use. Keep the whole thing under 200 words. Long prompts cost input tokens on every message, and they often make replies less consistent.

Change one thing at a time and rerun the same three test messages. If you edit the role and the format together, you will not know which change helped. Saving each version in a text file takes a minute and spares you from guessing later.

For adult fiction and companion use, set the age expectations in the prompt and in whatever sign-up flow you use around it. The model is tuned for lawful adult use, and the one fixed rule is that sexual content involving minors is never allowed.

Which option should you pick

If you want a general-purpose chat window for yourself or a small team, pick Open WebUI. It has a familiar layout, keeps your history locally and takes one command to start. If your goal is long character-driven stories or roleplay with lorebooks, pick SillyTavern, since it is built around that workflow. If you plan to turn the prototype into an app later, start with the LangChain snippet, because the same few lines grow into a real project.

None of these tools require a paid plan from this service. You top up only when the trial runs out, and you pay only for tokens you use. If you try one tool and it does not suit you, switch to another without changing your account, since the base URL, key and model ID stay the same everywhere.

Costs, limits and common problems

You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens from prepaid credit, with no subscription. A casual chat session of 20 messages, averaging 1,000 input tokens and 250 output tokens each, uses 20,000 input and 5,000 output tokens. That costs $0.003 plus $0.0025, so $0.0055. At that rate the $0.50 trial covers about 90 sessions. Failed or refused requests are not charged.

When you outgrow the trial, top-ups run from $20 to $500, with +5% from $50, +10% from $100 and +15% from $200, paid in USDT on TRC20 or USDC on Base. Credit never expires. The pricing page shows the full details.

If something fails

  • Empty model list or connection error: check the URL ends in /v1 with no trailing path, and that the key has no extra spaces.
  • 401: the key is wrong or missing.
  • 429 with code concurrency: a trial key allows 2 concurrent requests and 60 per minute. Close extra tabs or wait for streams to finish, because a streamed request holds its slot until it ends.
  • 429 with code rate_limited: you hit the per-minute limit. Wait a minute. A full key allows 8 concurrent and 300 per minute.
  • 429 with Retry-After: 5: temporary overload. Retry after five seconds.

Questions about the trial itself are answered in the free trial FAQ, and the API documentation lists the full parameter set. This service is text only, so image generation, voice and embeddings are not available in these tools through this endpoint.

Questions and answers

Do I need to know how to code?

No, if you use a ready-made chat tool such as Open WebUI or SillyTavern. You paste the base URL, your key and the model ID uncensored into its connection settings.

Can I put one of these tools on my public website?

They are standalone chat apps, not embeddable widgets. For a public site you need a small backend that keeps your key private, as shown in the web chat tutorial.

Which model ID do I enter?

Enter uncensored. You can confirm it by calling GET /v1/models with your key.

Is it free to try?

New users can claim $0.50 of trial credit with one click on the API key page, valid for 7 days. A trial key has lower limits: 2 concurrent requests and 60 per minute.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API keyRead the docs