EN ▾

Uncensored LLM API

Uncensored LLM API Pricing

Get transparent, token-based llm pricing for a single uncensored chat API. No hidden fees, no vendor lock-in, just pay for what you use.

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

uncensoredhttps://api.llmtokenprices.com/v1

Try it in one request

curl https://api.llmtokenprices.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

OpenAI-Compatible Endpoints

Use POST /v1/chat/completions for streaming and tool calling, and GET /v1/models to list available models. No embeddings, image, or audio generation.

Transparent Token Pricing

Pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. Prepaid credit never expires and rolls over automatically.

100k Context Window

Process up to 100,000 tokens per request (prompt + completion). Ideal for long documents or extended conversations without context loss.

Simple Pay-As-You-Go

No monthly subscriptions or usage tiers. Top up from $20 by crypto (USDT on TRC20, USDC on Base), or start with $0.50 trial credit.

Direct Integration

Works with official OpenAI SDKs by changing the base_url to our endpoint. Regenerate your API key instantly if compromised.

Uncensored & Private

Answers without refusals for lawful adult use. Prompts are not used for training. Only hard limit: no sexual content involving minors.

How it works

  1. Create Account

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

  2. Configure SDK

    Update your client's base_url to https://api.llmtokenprices.com/v1 and set your API key.

  3. Send Requests

    Make POST requests to /v1/chat/completions with model_id 'uncensored' and start generating text.

What people build with it

Content Generation

Generate uncensored stories, scripts, or creative writing without filter interruptions. Use streaming for real-time output delivery to users.

Data Annotation

Label datasets or extract entities from large text blocks using the 100k context window. Tool calling helps structure the output programmatically.

Chatbot Backend

Build a chatbot that remembers long conversations within the context limit. Pay only for the tokens consumed during user interactions.

Research & Analysis

Feed research papers or codebases into the model for analysis. The open-weight model handles diverse topics without content refusals.

Why Token-Based Pricing Matters

Traditional API pricing often bundles costs into complex tiers or subscription models that obscure the true cost of usage. Token-based llm pricing gives you exact visibility into what you pay for. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. This transparency lets you calculate costs precisely based on your input and output lengths.

Unlike subscription plans that charge for idle capacity, our pay-as-you-go model charges only for active usage. Prepaid credit never expires, so you never lose money from monthly renewals. This approach is ideal for developers who want to track exact spend without guessing.

Uncensored vs. Filtered Model Costs

Filtered models often refuse requests for lawful adult, fictional, or controversial topics, requiring manual overrides or multiple attempts. Our uncensored model answers directly, reducing the number of tokens wasted on refusals. You pay for the final answer, not the filtering process.

The only hard content limit is the blocking of sexual content involving minors. For all other lawful uses, the model provides direct responses. This reduces friction in your application flow and ensures consistent output for creative or research tasks.

API Features: Streaming & Tool Calling

The API supports two endpoints: POST /v1/chat/completions for chat interactions and GET /v1/models to list available models. Streaming via Server-Sent Events (SSE) enables real-time token delivery. Tool calling allows the model to execute functions during the conversation.

These features work with the official OpenAI SDKs by updating the base_url to https://api.llmtokenprices.com/v1. No other endpoints like embeddings or image generation are provided. This focus ensures a simple, reliable integration for text-based applications.

Pay-As-You-Go vs. Subscription Models

Subscription models charge a fixed monthly fee regardless of usage, which can be inefficient for intermittent workloads. Our pay-as-you-go model charges only for tokens consumed. Prepaid credit never expires, so you retain value even between projects. Top-ups start at $20 with bonuses for larger amounts.

New accounts receive $0.50 trial credit valid for 7 days. Claim this credit with one click on your API key page. No card is needed for the trial. This low barrier to entry lets you test the API's performance and pricing structure before committing to larger purchases.

How Our 100k Context Window Saves Money

A larger context window allows you to process more data in a single request, reducing the number of API calls needed. Our 100,000 token limit handles long documents or extended conversations without context loss. This efficiency lowers the total token count and reduces overall costs.

For example, summarizing a large book or analyzing a lengthy codebase requires fewer requests than with smaller context windows. Each request costs based on token volume, so fewer requests mean lower bills. The 100k window maximizes throughput per dollar spent.

Developer Experience & SDK Compatibility

The API is designed for easy integration. Use the official OpenAI SDKs by setting the base_url and API key. The model ID is 'uncensored'. Requests are limited to 300 per minute per key, with an 8 MB body limit. One key per account, easily regenerated.

Privacy is prioritized: prompts are not used for training. Accounts require only email and password. No phone number or card is needed for the trial. This simplicity reduces integration time and allows developers to focus on building features rather than managing complex API configurations.

Who This Is NOT For

If you need embeddings, image generation, audio processing, or fine-tuning, this API is not the right choice. We do not offer model routing, SLA guarantees, or SOC2/HIPAA certifications. We do not host multiple vendor models. This service is for developers who need a single, uncensored text model with transparent, token-based pricing. If you require high-availability enterprise features or multi-modal capabilities, look elsewhere.

Questions and answers

What are the exact endpoints supported?

The API supports two endpoints: POST /v1/chat/completions for chat interactions and GET /v1/models to list available models. It does not support embeddings, image, audio, or video generation. Streaming and tool calling are available via the chat completions endpoint.

Does paid credit expire?

No. Prepaid credit never expires. You can top up from $20 by crypto (USDT on TRC20, USDC on Base). Bonuses are applied at $50 (+5%), $100 (+10%), and $200 (+15%). There are no monthly fees or usage limits that cause credit to vanish.

How does the trial work?

New users get $0.50 of trial credit, one per person, valid for 7 days. Claim this credit with one click on your API key page. No card or phone number is needed. You can use it to test the API. After the trial expires, you can add paid credit to continue usage without interruption.

What content is blocked?

The only hard limit is the blocking of sexual content involving minors. For all other lawful adult, fictional, or controversial topics, the model provides direct responses without refusals. Prompts are not used for training.

Is it compatible with OpenAI SDKs?

Yes. Update the base_url to https://api.llmtokenprices.com/v1 and set your API key. The model ID is 'uncensored'. This works with the official OpenAI SDKs and any OpenAI-compatible client.

Your key is one form away

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

Get API key