Uncensored LLM API

Ollama api doc: Uncensored Alternative API

Use our cheap LLM API with a 100,000 token context window for uncensored responses, replacing standard providers with a prepaid crypto model that never expires.

$0.15 per 1M input tokens
Crypto top-up only
300 requests per minute

Start now View documentation

Test with one call

curl https://api.ollamaapidoc.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all installed models"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.ollamaapidoc.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)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.ollamaapidoc.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

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

Core features

OpenAI Compatible

Works with existing OpenAI SDKs by changing the base URL and API key.

Uncensored Model

Answers without content refusals for lawful adult use, fiction, or security research.

No Subscription

Prepaid credit never expires, with errors and refusals charged at zero tokens.

Crypto Only

Top up with USDT or USDC, receiving bonus credit on larger amounts.

Large Context

Supports a 100,000 token context window for long document processing workflows.

Streaming & Tools

Supports SSE streaming, function calling, and JSON mode for complex apps.

Setup process

Get Key

Top Up

Add crypto credit starting from $20 to activate your account for use.

Send Requests

Point your OpenAI client to our base URL and start sending prompts.

Community projects

NSFW Roleplay

Run unrestricted character interactions without standard filters blocking adult narrative content.

Local Data Parsing

Clean and parse Word docs for text extraction without weird characters breaking the model.

Dev Workflow

Use uncensored models for coding assistance without moralizing or restrictive output formatting.

Privacy First

Pay with crypto and avoid linking your identity to your AI usage patterns.

Common mistakes people make in this niche and how to avoid them

Developers often assume local models lack API compatibility, yet our endpoint mirrors OpenAI standards exactly. Another error is ignoring context limits; our 100k window handles complex documents without truncation errors. Users also overpay by subscribing to monthly plans when prepaid tokens offer better value. We eliminate hidden fees by charging only for actual usage, ensuring transparent costs for uncensored workflows.

ollama API doc: The Uncensored Alternative

Our API provides a direct, uncensored endpoint that works with your existing OpenAI SDK code.

Roleplay & Creative Writing

Get unrestricted responses for NSFW or controversial topics without hidden refusals.

Local Data Parsing

Handle messy text extraction from Word docs directly via our hosted service.

Privacy-First Development

Pay with crypto, keep your prompts private, and avoid monthly subscription locks.

Checklist for Choosing an Uncensored LLM Provider

Verify token pricing transparency before committing. Ensure the endpoint is fully OpenAI-compatible for easy SDK swaps. Confirm uncensored behavior for your specific use case, not just marketing claims. Check rate limits and concurrent request caps. Validate that prepaid credit never expires. Avoid providers locking you into monthly subscriptions. Prefer crypto payments for privacy. Test with a low-cost trial key first.

Who uses it, in which real situations; and plainly who it is NOT for

Developers using NSFW chatbots, roleplay creators, and local AI enthusiasts use this API for unrestricted text generation. It fits workflows needing OpenAI-compatible syntax without content filters. It is NOT for teams requiring embeddings, image generation, or fine-tuning. Users needing multi-model routing or SLA guarantees should look elsewhere. This endpoint serves single-model, uncensored text tasks only.

Worked cost examples with token arithmetic that use only our prices

Costs scale strictly with token volume at $0.15 per million input tokens and $0.50 per million output tokens. For example, a 5,000-token prompt plus a 2,000-token response totals 7,000 tokens, costing exactly $0.00105. Errors and refusals incur zero charges, preserving your prepaid credit. This predictable structure helps you budget accurately without hidden fees or subscription locks.

What developers actually ask about this topic

What is the context window and output limit?

Our API supports a 100,000-token context window, with a maximum output of 16,000 tokens per request.

How do I handle streaming?

We use Server-Sent Events (SSE) to stream responses, including token usage details in the final chunk.

Does it support function calling?

Yes, our endpoint handles tools and tool_choice parameters for structured interactions.

What is the price per token?

You pay $0.15 per million input tokens and $0.50 per million output tokens, with no hidden fees.

Common questions

What is the ollama API doc endpoint for chat completions?

It is POST /v1/chat/completions. This endpoint handles text in and text out. It works with standard OpenAI SDKs by changing the base URL. No embeddings or image generation are available.

Is there a monthly subscription fee?

No. There is no monthly subscription fee. You pay only for tokens used. Errors and refusals are free. Credit never expires, so you can top up whenever needed without urgency.

How do I pay for my API credits?

You pay via crypto only. We accept USDT on TRC20 or USDC on Base. Payments range from $20 to $500. Bonuses apply to larger top-ups.

What is the context window limit?

The context window is 100,000 tokens. This includes both prompt and completion together. Max output is 16,000 tokens per request. If you do not set max_tokens, the limit drops to 2,048 tokens.

Can I stream responses?

Yes, streaming is supported via SSE. Token usage appears in the final chunk. This allows real-time output for your application. Function calling and JSON mode are also available for structured data.

Do you use prompts for training?

No, your prompts are not used for training. Privacy is maintained for your data. You need only an email for your account. No phone number is required to get started immediately.

Get your key in seconds

Start now