EN ▾
Get API key
Direct API Access

The Uncensored LLM API for Unrestricted Text Generation

Build text roleplay around a scene state that your application controls. Send character details and allowed choices with each request, then validate the response before advancing the conversation.

  • OpenAI SDK compatible
  • Content review
  • Pay-as-you-go pricing

Try it in one request

curl https://api.uncensoredllmapi.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."}]
  }'
per 1M input tokens
$0.15
Output tokens / 1M
$0.50
token context
100,000
trial credit
$0.50
requests per minute
300

What you get

  1. OpenAI Compatible

    Drop into your existing stack. Use the standard /v1/chat/completions endpoint with any OpenAI-compatible client or SDK.

  2. One text model

    Use the public model ID uncensored, then check the reply against the character brief and scene constraints.

  3. Transparent Pricing

    No monthly fees. Pay only for tokens used with paid credit that does not expire. Trial credit has a separate 7-day validity period.

  4. Large Context

    Supports 100,000 tokens per request for long-form roleplay and document processing.

  5. Streaming Support

    Enable real-time responses via Server-Sent Events (SSE) for chat-like user experiences.

  6. Simple Keys

    One API key per account. Regenerate instantly if needed without losing your data or balance.

How it works

  1. Create Account

    Sign up with email and password to receive your API key and $0.50 trial credit. Claim this credit with one click on your API key page.

  2. Configure Client

    Set your base URL to https://api.uncensoredllmapi.com/v1 and inject your API key.

  3. Send Requests

    Call the chat completions endpoint with model ID "uncensored" and start generating content.

What people build with it

Why Use an Uncensored LLM API?

Use an uncensored llm api when you need a text model behind a Chat Completions client. This service exposes one public model ID, not a catalogue of vendors. Request format compatibility does not guarantee identical answers. For roleplay, validate names, events and allowed actions against your stored scene state.

OpenAI Compatible Endpoints

We adhere strictly to the OpenAI API structure. You can use the official OpenAI SDKs for Python, Node.js, and other languages with minimal configuration. Simply change the base URL to our endpoint and provide your API key. We support streaming via Server-Sent Events (SSE) and tool/function calling for advanced agent workflows. There are no embeddings, image generation, or fine-tuning endpoints—just pure text completion. This simplicity reduces integration time and debugging overhead. If you are already building with OpenAI, switching to us is a matter of updating your base URL and model ID.

curl https://api.uncensoredllmapi.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.uncensoredllmapi.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)

Unrestricted Content & Roleplay

Provide a scene summary, adult character descriptions and the choices allowed at this step. Validate the generated reply against that state and keep conversation storage in your own application.

Developer-Friendly Features

Use one active API key per account. Regenerating it revokes the old key. Pricing is $0.15 per million input tokens and $0.50 per million output tokens, with paid top-ups from $20 to $500. Eligible accounts can request a $0.50 trial for 7 days. The statement about no training on prompts does not establish zero retention or complete confidentiality.

Questions and answers

Is this API suitable for NSFW content?

The model can be used for fictional adult-character dialogue within the service’s rules. It can still refuse or produce an unsuitable reply. Review output in your application; sexual content involving minors is prohibited.

Does it work with the OpenAI Python SDK?

Yes. It is fully compatible with the OpenAI SDK. You only need to update the base URL to https://api.uncensoredllmapi.com/v1 and set your API key. The request format is identical to standard OpenAI chat completions.

What is the pricing for the uncensored llm api?

We use a pay-as-you-go model. Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. There are no monthly subscriptions or hidden fees. paid credit does not expire. Trial credit has a separate 7-day validity period.

How long is the context window?

The model supports a context window of 100,000 tokens. This includes both the prompt and the completion, allowing for long-form interactions and large document analysis.

Is this API for me if I need image generation?

No. This is a text-only API. We do not offer image, audio, or video generation. If you need multimodal capabilities, this API is not the right choice for those specific tasks.

Your key is one form away

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

Example: keep a branching roleplay scene consistent

Supply a fictional scene summary, a list of adult characters and two allowed choice IDs: stay or leave. Request a JSON object containing a short reply, selected_choice and continuity_notes. Validate the selected choice against that list and compare the reply with the supplied scene state. Keep session memory and content boundaries in your application. This example checks a branching dialogue step; the API does not manage the game state for you.