EN ▾
Get API key

Uncensored Text API

Embedding API companion: an uncensored LLM for chat

A dedicated text-completion endpoint for RAG pipelines. Integrate an uncensored model into your embeddings workflow without content refusals.

Get API keyRead the docs

OpenAI-compatible chat completions

100k token context window

No training on prompts

$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute

Try it in one request

curl https://api.embeddingapis.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."}]
  }'

What you get

Text-Only Focus

We provide a single uncensored model for text generation. We do not generate images, audio, video, or embeddings.

OpenAI Compatible

Use the official OpenAI SDK with our base URL. Point your existing code to our endpoint for immediate integration.

Uncensored Output

The model answers without refusing lawful adult, fictional, or controversial topics. Only minor sexual content is blocked.

Privacy First

Prompts are not used for training your model. Only an email and password are required to start.

Simple Pricing

Pay only for tokens used. No monthly fees or subscriptions. Credit never expires.

Stream Support

Get real-time responses via Server-Sent Events. Tool calling is fully supported for agentic workflows.

How it works

  1. Sign Up

    Create an account with email and password to receive your API key instantly.

  2. Configure SDK

    Update your client base_url to our endpoint and set your API key.

  3. Send Requests

    Call /v1/chat/completions with your uncensored model ID and process the text.

What people build with it

RAG Post-Processing

Use the API to summarize or extract data from retrieved chunks. Avoid refusals when processing sensitive but lawful documents.

Agent Prompting

Route agent decisions to an uncensored model for reliable instruction following. Ensure outputs match your pipeline logic exactly.

Content Generation

Generate scripts, captions, or creative text without content filters. Ideal for adult or niche content pipelines.

Data Extraction

Parse unstructured text into structured formats. The model follows instructions precisely without extra conversational filler.

Why Use an Uncensored API for Text Tasks?

Standard models often refuse lawful adult, controversial, or niche topics. Our embeddings api pipeline benefits from a text model that answers directly. We use an open-weight model tuned for uncensored output. It does not refuse based on common content policies. This ensures your pipeline processes prompts exactly as intended. You avoid unexpected refusals during post-processing or extraction. The model supports tool calling and streaming. This makes it suitable for complex agentic workflows. Note that sexual content involving minors is still blocked. This is the only hard limit applied to all requests.

Seamless OpenAI SDK Compatibility

Our API follows the OpenAI chat completions standard. You can use the official OpenAI SDK by updating the base URL. This allows you to integrate our uncensored model into your existing code. Streaming responses are supported via Server-Sent Events. Tool calling is available for building AI agents. The model ID is uncensored. This ensures compatibility with your current pipeline structure. You do not need to rewrite your client code. Just update the endpoint and key.

Text-Only Focus: Complements Your Embeddings Stack

This API is for text generation only. It does not handle embeddings, images, audio, or video. Use it for the text steps in your pipeline. For example, summarize retrieved chunks or extract entities. This complements your vector database workflow. You get reliable text output for your embeddings. The model has a 100,000 token context window. This supports long documents in your RAG pipeline. It is not a replacement for your embedding model. It is a complement for text processing tasks.

Pricing: Pay Only for Tokens Used

We offer simple pay-as-you-go pricing. There are no monthly fees or subscriptions. You pay for input and output tokens. The cost is $0.15 per 1M input tokens. Output tokens cost $0.50 per 1M tokens. Prepaid credit never expires. You can top up from $20. Bonuses are available for larger deposits. New accounts get $0.50 in trial credit. Claim this credit with one click on your API key page. No credit card is needed for the trial. This makes it easy to test the API. You only pay for what you use.

Questions and answers

What is the uncensored model?

It is an open-weight model run on our GPU servers. It is tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model. Sexual content involving minors is blocked.

Do you use prompts for training?

No, your prompts are not used for training. We only require an email and password for your account. This ensures your data remains private. You can use the API for sensitive content without worry.

Can I stream responses?

Yes, streaming is supported via Server-Sent Events. This allows real-time token delivery to your client. It is ideal for agentic workflows and chat interfaces. Use the standard OpenAI streaming format.

What are the rate limits?

You can send 300 requests per minute per key. The request body limit is 8 MB. Each account has one key that can be regenerated. This ensures fair usage across all customers.

Is this for image generation?

No, we do not generate images, audio, video, or embeddings. This is a text-completion API. Use it for post-processing, summarization, or extraction. It complements your embeddings stack for text tasks.

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

Guides

Practical articles on setup, pricing and integration.

All guides →