Drop-in Uncensored LLM

Open ai compatible uncensored API

Get an open AI compatible endpoint with 100k context for zero-refusal content, switching base_url and key keeps your existing code intact.

100,000 token context window
No monthly subscription fees
Crypto top-up only

Create key View documentation

Test with a single request

curl https://api.compatibleaiopen.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List three benefits of local inference"}]
  }'

from openai import OpenAI

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

Key features

Standard Endpoint

POST /v1/chat/completions works with any OpenAI SDK client out of the box.

Uncensored Output

Open-weight model answers without refusals for lawful adult, fictional, or research topics.

Streaming Support

SSE streaming includes token usage data in the final chunk for accurate billing.

Tool Use Ready

Function calling and JSON mode enabled via standard parameters like tool_choice.

Transparent Pricing

Pay only for real tokens used; errors and refusals cost zero credits.

Instant Access

Get your API key immediately via Google or email without phone verification.

Setup process

Get Your Key
Sign up with Google or email to receive your active API key instantly.
Update Configuration
Change your base_url to our endpoint and set your new API key.
Send Requests
Call the chat completions endpoint and receive uncensored text responses immediately.

Common use cases

Local Stack Integration

Replace llama-server or vLLM endpoints with this compatible API for local-first workflows.

Chatbot Pipelines

Connect tools like SillyTavern for unrestricted roleplay or creative writing sessions.

Research Ingestion

Process large documents within the 100k context window without content filters.

Cost-Conscious Scaling

Avoid monthly fees by topping up with crypto bonuses for high-volume usage.

How this differs from a typical alternative

We offer a single, uncensored model via a standard endpoint, avoiding complex routers or monthly subscriptions. Unlike typical gateways, we charge only for real token usage with transparent per-token pricing.

Feature	Typical Alternative	Ours
Pricing	Monthly subscriptions	Pay per token
Models	Multiple, routed	One uncensored model
Complexity	Complex routers	Drop-in compatible

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

Developers use this uncensored LLM for local-first stacks where standard refusals break pipelines. Change your base_url and keep the code, even when switching from llama-server to vllm. It fits research, creative writing, and apps needing unfiltered responses without complex routers. It is NOT for teams needing image generation, embeddings, or multi-model routing. Use it when you want a single, direct endpoint for text-only tasks.

Drop-in open AI compatible integration

Drop-in open AI compatible integration means you change the base URL and API key, then keep your existing code exactly as written.

Standard SDK Swaps

Point the official OpenAI SDK to HTTPS://api.compatibleaiopen.com/v1. You get a direct chat-completions endpoint without modifying your request logic.

Local Stack Compatibility

This API mirrors the standard OpenAI server interface. You can swap in llama.cpp or vLLm later while maintaining the same client structure.

Streaming Support
Enable streaming to receive server-sent events. The final chunk contains the complete token usage data for accurate billing tracking.

What developers actually ask about this topic

Is this a drop-in replacement for OpenAI?

Yes. Change your base_url to https://api.compatibleaiopen.com/v1 and your API key. Keep the SDK code identical.

Does it support streaming?

We support Server-Sent Events. Token usage appears in the final chunk.

What about local tools?

Use the same /v1/chat/completions endpoint structure that llama-server exposes.

This works with SillyTavern and similar clients by pointing them to our URL.

Worked cost examples with token arithmetic

Our pricing is transparent: $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals cost nothing. A typical 20k prompt with 2k output uses 22,000 tokens, totaling $0.0137. The trial credit covers many such requests. You can see exact token counts in the final streaming chunk. This predictable metering helps you budget accurately without hidden subscription fees.

Checklist for choosing a provider

Verify endpoint compatibility before integration. Our API uses the standard /v1/chat/completions path, so you only change the base URL and key. Check token pricing transparency; we charge $0.15 per 1M input tokens and $0.50 per 1M output tokens with no hidden fees. Ensure the uncensored model fits your use case by testing a few prompts. Confirm payment flexibility with our crypto-only top-ups starting at $20. Finally, verify the 100,000 token context window meets your data needs.

Common questions

What is an open AI compatible API?

It is a chat endpoint that accepts standard OpenAI SDK requests. You change the base URL and key, then keep your existing code. This endpoint serves one uncensored model with no complex routing or additional middleware required for integration.

Does it support streaming responses?

Yes, streaming is supported via Server-Sent Events. Token usage details are included in the final chunk. This allows real-time text rendering in your application while maintaining the standard response format expected by most modern client libraries and frameworks.

What is the context window size?

The context window is 100,000 tokens for both prompt and completion combined. Max output is 16,000 tokens per request. If you do not set max_tokens, the limit defaults to 2,048 tokens. This allows for substantial conversation history retention.

How do I add credit to my account?

You top up using crypto only, specifically USDT on TRC20 or USDC on Base. Minimum amounts start at $20. Bonus credit applies from $50 upwards. Your paid credit never expires, so you can use it whenever you are ready.

Is there a free trial available?

Yes, every new account receives $0.50 of trial credit. It allows you to test the API endpoint and verify integration with your existing local or cloud stack.

Can I use function calling tools?

Yes, the API supports function calling with tools and tool_choice parameters. You can also enforce JSON mode using response_format. This enables structured data extraction and tool execution within your application workflows without needing external parsing logic for complex outputs.