Uncensored OpenAI-compatible API for developers

Ollama API: an independent guide and a drop-in alternative

A drop-in, uncensored OpenAI-compatible API for developers who want no content filters and crypto payments. Swap your base URL and key to run the same client code with a dedicated uncensored model.

OpenAI-compatible endpoints
Crypto payments only
No content filters

Get API key Read the docs

Try it in one request

curl https://api.ollamaapi.cc/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.ollamaapi.cc/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.ollamaapi.cc/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);

$0.25per 1M input tokens
$1.00Output tokens / 1M
64,000token context
$0.50trial credit
300requests per minute

What you get

OpenAI Compatible
Uses standard /v1/chat/completions endpoints, so you only change the base URL and API key to integrate.
Uncensored Model
A dedicated open-weight model tuned to answer without refusals for lawful adult, fictional, or controversial topics.
Crypto Payments
Top up with USDT (TRC20) or USDC (Base). No cards, no subscriptions, and credit never expires.
Function Calling
Supports tools, tool_choice, and JSON mode for robust programmatic integration with your applications.
Large Context
Handle long inputs with a 64,000 token context window and generate up to 16,000 tokens per request.
Streaming Support
Receive real-time responses via Server-Sent Events (SSE) with token usage details in the final chunk.

How it works

Create Account
Sign up with Google or email to get your API key instantly without a phone number.
Top Up with Crypto
Add credit using USDT or USDC; errors are free and prepaid credit never expires.
Start Coding
Update your SDK base_url to api.ollamaapi.cc and send your first request immediately.

What people build with it

Content Generation
Generate creative fiction, roleplay, or adult content without the model refusing based on standard safety filters. Ideal for applications where nuance matters more than brand safety.
API Integration
Drop this uncensored API into existing OpenAI SDK workflows by simply changing the base URL. No code changes required for function calling or streaming.
Data Analysis
Process large documents with a 64k context window. Get direct answers without the model refusing to process sensitive or controversial data structures.
Developer Testing
Test your applications against an uncensored model to see how your prompts perform without standard refusals interfering with your logic.

Why Ollama API?

Many developers search for the ollama api because they want local control, but others need a reliable hosted uncensored LLM that integrates with existing tooling. This service provides a dedicated, uncensored model via OpenAI-compatible endpoints. Unlike generic providers, we focus on a single, high-quality uncensored model that does not refuse lawful adult or controversial topics.

We prioritize developer experience with crypto payments and no expiration on prepaid credit. You can swap in our API by changing just the base URL and key. This is not an official Ollama site; it is an independent guide and a drop-in alternative for developers who need uncensored text generation without content filters.

OpenAI Compatible Endpoints

Our API implements the standard OpenAI protocol, ensuring compatibility with official SDKs and any OpenAI-compatible client. You will use POST /v1/chat/completions for generation and GET /v1/models to list available models. The only model available is uncensored, an open-weight model run on our servers.

Endpoints: Chat completions and model listing only.
No extra features: We do not offer embeddings, image, audio, or video generation, or fine-tuning.
Parameters: Supports temperature, top_p, stop, seed, presence_penalty, and frequency_penalty.

This simplicity allows you to integrate quickly without learning a new API structure.

Uncensored Performance

The uncensored model is tuned to answer without content refusals for lawful adult use. It handles fictional, security-research, and controversial topics effectively. While it is uncensored, it does block sexual content involving minors, which is a hard limit that always applies.

This makes it ideal for applications where standard safety filters might interfere with creative or niche use cases. The model is not GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama, or any other vendor's model. It is a distinct, open-weight model designed for flexibility. You can use it for content generation, roleplay, or data processing where refusals are a bottleneck.

Developer Integration

Integrating our API requires minimal code changes. You simply update the base_url in your OpenAI SDK to https://api.ollamaapi.cc/v1 and provide your API key. The model ID to send is uncensored. This approach works with any client that supports the OpenAI protocol.

Streaming: Use SSE for real-time responses with token usage in the last chunk.
Function Calling: Supports tools and tool_choice for structured outputs.
JSON Mode: Enforce structured outputs with response_format json_object.

This compatibility means you can test our uncensored model in your existing pipeline without rewriting your integration logic.

Pricing & Crypto Payments

We charge by real token usage: $0.25 per 1M input tokens and $1.00 per 1M output tokens. Errors and refusals are free. There is no subscription or monthly fee, and prepaid credit never expires. You can top up with USDT (TRC20) or USDC (Base) in whole amounts from $10 to $500. You receive a +5% bonus on $50 and a +10% bonus on $100.

Each new account gets $0.50 of trial credit valid for 7 days, no card needed. We do not accept cards, PayPal, or bank transfers. If you make a mistake like a double charge, use the Support page to fix it. Credit is not refunded, but it remains available indefinitely.

API Limits & Features

Our API has specific limits to ensure stability. You are allowed 300 requests per minute per key and 8 concurrent requests per key. The maximum request body size is 8 MB. You get one active key per account; generating a new key replaces the old one.

The context window is 64,000 tokens for prompt and completion combined. The max output is 16,000 tokens per request, or 2,048 if max_tokens is not set. We do not offer SLAs, SOC2/HIPAA/ISO certifications, or on-prem deployment. This is an API for developers, not a consumer chat app. If you need embeddings, image generation, or fine-tuning, this API is not for you.

Get Your Key

Sign up with Google or an email and password to get your API key immediately. No phone number is required. Once you have your key, you can start sending requests right away. Use the uncensored model ID with your preferred OpenAI-compatible SDK. Top up with crypto to add credit, which never expires. This is the fastest way to get an uncensored LLM API for your projects.

Questions and answers

Is this the official Ollama API?

No, this is an independent service. We provide a hosted, uncensored model that is compatible with the OpenAI API protocol. We are not affiliated with Ollama, OpenAI, or any other model provider. We serve our own open-weight model designed for uncensored responses.

What crypto payments do you accept?

We accept USDT (TRC20) and USDC (Base). You can top up with any whole amount from $10 to $500. We do not accept credit cards, PayPal, or bank transfers. Prepaid credit never expires, and you get bonuses for larger top-ups.

Does the uncensored model refuse prompts?

It is tuned to answer without content refusals for lawful adult, fictional, or controversial topics. However, it does block sexual content involving minors, which is a hard limit. It does not refuse based on standard safety filters like many other models.

Can I use this with the official OpenAI SDK?

Yes, our API is OpenAI-compatible. You only need to change the base URL to https://api.ollamaapi.cc/v1 and provide your API key. The model ID to use is <code>uncensored</code>. This works with any client that supports the OpenAI protocol.

What are the rate limits?

You can make 300 requests per minute and have 8 concurrent requests per key. The maximum request body size is 8 MB. You get one active API key per account. If you generate a new key, it replaces the old one.

Your key is one form away

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

Get API key

Ollama API: an independent guide and a drop-in alternative

Try it in one request

What you get

OpenAI Compatible

Uncensored Model

Crypto Payments

Function Calling

Large Context

Streaming Support

How it works

Create Account

Top Up with Crypto

Start Coding