EN ▾
Get API key

Uncensored LLM API with OpenAI compatibility

Uncensored Chatbot API for Character Chat Apps

A single, high-quality uncensored model with an OpenAI-compatible interface. No subscriptions, no hidden fees, just raw text generation for your chatbot.

Get API keyRead the docs

  • OpenAI-compatible chat endpoint
  • No content filters for lawful use
  • $0.15 per 1M input tokens

Try it in one request

curl https://api.characteraiapi.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

OpenAI Compatibility

Drop this API into existing OpenAI SDKs by changing the base URL. Supports streaming via SSE and tool/function calling out of the box.

Single Uncensored Model

We serve one open-weight model tuned for unrestricted creative writing and roleplay. It does not refuse lawful adult or controversial topics by default.

Transparent Pricing

Pay-as-you-go prepaid credit with no monthly fees. Credits never expire, and you only pay for the tokens you actually use.

Large Context Window

Supports a 100,000 token context window for both prompt and completion, allowing for long-form conversations and detailed context retention.

Simple Privacy

Prompts are not used for training. Account setup requires only an email and password, with no phone number or credit card needed for the trial.

Immediate Access

New accounts receive $0.50 in trial credit valid for 7 days. Claim this credit with one click on your API key page. No card required, and your API key is shown immediately after signup.

How it works

  1. Create Account

    Sign up with your email and password to receive your API key instantly.

  2. Configure Client

    Update your OpenAI SDK configuration to point to our base URL and use your new key.

  3. Start Generating

    Send requests to the chat-completions endpoint and receive uncensored text responses.

Uncensored LLM API with OpenAI compatibility

What people build with it

Roleplay Chatbots

Build immersive characters that stay in context without breaking character due to content filters. Ideal for interactive fiction and companion apps.

Creative Writing Assistants

Generate stories and scripts that explore mature themes without artificial restrictions on vocabulary or narrative direction.

Research & Analysis

Use the model for uncensored summarization or analysis of controversial topics where standard models might apply unnecessary bias or refusal.

Data Generation

Produce large volumes of diverse text data for training or testing other systems without worrying about output filtering.

What is the Character AI API?

This API provides access to a single, open-weight large language model optimized for unrestricted text generation. Unlike providers that offer a mix of models, we focus exclusively on one uncensored model that answers without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model; it is a distinct open-weight model run on our own GPU servers.

The service is designed for developers who want raw model access without the noise of multiple options. You get a consistent behavior pattern: the model does not filter lawful adult, fictional, security-research, or controversial topics by default. However, a hard content limit always applies: requests involving sexual content with minors are blocked.

Why Choose an Uncensored LLM?

Standard LLMs often refuse valid prompts because they interpret nuanced or mature topics as violations. An uncensored API removes these arbitrary barriers, giving you full control over the output. This is critical for creative writing, roleplay, and applications where the model needs to explore darker or more complex themes without breaking immersion.

By using a dedicated uncensored model, you avoid the variability of routing or fine-tuning. The behavior is consistent and predictable. Note that while we do not filter heavily, we do block specific hard limits like sexual content involving minors. This API is not for you if you require image generation, audio processing, or embeddings—this is strictly a text-in, text-out service.

OpenAI-Compatible Interface

We use the standard POST /v1/chat/completions endpoint, meaning you can switch from OpenAI to our API by changing two lines of code: the base URL and the API key. We support streaming via Server-Sent Events (SSE) and tool/function calling, matching the features developers expect from major providers.

The model ID is simply "uncensored". This consistency allows you to use the official OpenAI SDKs or any OpenAI-compatible client. You get a 100,000 token context window, which handles both prompt and completion tokens. There are no embeddings, no image generation, and no fine-tuning endpoints—just reliable, high-speed text generation.

Pricing: Pay Only for What You Use

Our pricing is transparent and usage-based: $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no subscription fees, no monthly locks, and no hidden costs. You top up with prepaid credit, which never expires. You can start with a free trial of $0.50 for 7 days, no card required. Claim this credit with one click on your API key page.

For larger needs, we offer bonus credit: +5% on top-ups of $50, +10% on top-ups of $100, and +15% on top-ups of $200. Payments can be made by crypto (USDT on TRC20, USDC on Base). Limits are set to 300 requests per minute per key and an 8 MB request body. This model is not for you if you need guaranteed SLA percentages, SOC2 certifications, or on-prem deployment. It is built for developers who want cost-effective, predictable scaling.

Questions and answers

Is this the best uncensored llm available?

We do not claim our model is the "best" uncensored LLM, as that is a subjective and unverified superlative. We offer a single, high-quality open-weight model optimized for unrestricted creative writing and roleplay. Its performance depends on your specific use case and requirements for context length and response style.

Does the model filter all adult content?

No, the model does not filter lawful adult, fictional, or controversial topics by default. It is tuned to answer without content refusals. However, there is one hard content limit that always applies: requests involving sexual content with minors are blocked.

Can I use this with the official OpenAI SDK?

Yes. Our API is fully OpenAI-compatible. You can use the official OpenAI SDKs for Python, Node, and other languages by simply updating the base URL to https://api.characteraiapi.com/v1 and providing your API key. We support streaming and function calling.

What is the context window size?

The model supports a 100,000 token context window. This total covers both the input prompt and the output completion, allowing for long conversations and detailed context retention without needing external memory management.

Do you use my prompts for training?

No. Your prompts are not used for training. We require only an email and password to create an account, and we do not collect phone numbers or require a credit card for the trial period. Your data usage is transparent and minimal.

Your key is one form away

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

Get API key

Guides

Practical articles on setup, pricing and integration.

All guides →