OpenAI-Compatible API
Unrestricted AI Bot: The Uncensored LLM API
Get the unrestricted AI bot API for text generation with a 100,000 token context window and transparent per-token pricing.
- 100,000 token context window
- No subscription or monthly fees
- $0.50 per 1M output tokens
Test with a single request
curl https://api.unrestrictedaibot.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Find all null values in this JSON response"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.unrestrictedaibot.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.unrestrictedaibot.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);Core capabilities
Uncensored Text API
The model answers without content refusals for lawful adult topics.
Standard Compatibility
Works with official OpenAI SDKs by changing the base URL and key.
Function Calling Support
Use tools, tool_choice, and JSON mode for structured data extraction.
Streaming via SSE
Receive real-time tokens with usage data in the final chunk.
Crypto Top-ups Only
Add funds with USDT or USDC for a bonus credit percentage.
Simple Rate Limits
Get 300 requests per minute with no hidden constraints or quotas.
Setup guide
Get Your Key
Sign up with Google or email to receive your API key instantly.
Update Base URL
Point your SDK to HTTPS://api.unrestrictedaibot.com/v1 in your code.
Send Requests
Call the endpoint with model "uncensored" and start generating text.
Real-world integrations
Raw Data Extraction
Parse JSON responses without formatting restrictions or content filters.
Creative Writing
Generate stories and dialogue with full freedom from topic refusals.
Security Research
Test model behavior on controversial topics without unexpected blocking.
Custom Chatbots
Build character-driven bots that respond naturally without canned answers.
4 concrete signs you have hit a walled garden
Walled gardens restrict your output. Ours is an uncensored LLM API with no hidden constraints.
| Constraint | Typical Walled Garden | Our Uncensored API |
|---|---|---|
| Content Filters | Refuses lawful adult topics | No refusals for adult use |
| Pricing | High output costs | $0.50 per 1M output tokens |
| Usage Limits | Strict rate limits | 300 requests per minute |
| Token Count | Varies by tier | 100,000 context window |
Introducing the unrestricted AI bot for developers
The unrestricted AI bot delivers a single, open-weight model that answers without content refusals for lawful adult use.
Raw Text Output
Get raw text via POST /v1/chat/completions without paragraph-heavy refusals.
Standard Compatibility
Swap your base_url and keep using existing OpenAI SDKs for function calling and streaming.
Predictable Costs
Pay only for tokens used; errors and refusals are free with prepaid crypto credit.
Connect your code in 4 simple steps
Connect your code in 4 simple steps
Get your first uncensored response by following these four clear steps.
- Sign up instantly using your Google account or a simple email address.
- Retrieve your unique API key from the dashboard without any phone verification.
- Update your SDK configuration to point to
https://api.unrestrictedaibot.com/v1. - Send a
POSTrequest with the model ID"uncensored"to receive text output.
Calculate your spend with real token examples
You pay only for tokens actually consumed, not for refused responses. Input costs $0.15 per million tokens, while output is $0.50 per million. For example, a 5,000-token prompt paired with a 1,000-token completion costs just $0.00325. Errors are free. This transparent, per-token model ensures you never overpay for empty refusals or unused capacity.
Stop paying for refusals and rate limits
Our uncensored LLM API charges only for successful token usage, eliminating waste on refusals. Unlike standard providers that bill for every attempt, errors remain free. You also gain 300 requests per minute and 8 concurrent connections per key, preventing throughput bottlenecks during high-volume processing. This transparent model ensures you pay strictly for output, not for the model’s hesitation or infrastructure limits.
Migrate your OpenAI key in 3 lines
Migrate your OpenAI key in 3 lines
Switch your code to the unrestricted AI bot in three simple steps. First, replace your base URL with our hosted endpoint. Second, update your API key to the one generated on your dashboard. Third, keep your existing SDK version because our service is fully OpenAI-compatible. You can start sending requests immediately with zero configuration changes.
Common questions
What is an unrestricted AI bot and how does it differ from standard models?
It is a hosted API serving a single uncensored large language model. Unlike standard models, it does not refuse lawful adult, fictional, or controversial topics. You send text in and receive text out via standard endpoints.
Does the uncensored AI API support streaming responses?
Yes. The API supports streaming via Server-Sent Events. You can access token usage details included in the final chunk. This allows real-time text generation similar to popular chat interfaces without waiting for full completion.
Is there a minimum amount required to top up credit?
No. The minimum top-up is twenty dollars in crypto. You can add any whole amount up to five hundred dollars. Bonus credit applies automatically at higher tiers, starting with a five percent bonus at fifty dollars.
Can I use this API with existing OpenAI SDKs?
Yes. It is fully compatible with official OpenAI libraries. You only need to update the base URL and API key. The endpoint structure matches standard chat-completions, ensuring immediate integration with your current codebase without major changes.
Are prompts used to train the model?
No. Your prompts are not used for training. The service maintains strict privacy regarding your data. You can send sensitive or proprietary text without worrying about it being ingested into the model weights for other users.
What happens if the API returns an error?
You are not charged for errors or refusals. You only pay for real token usage. This means failed requests do not deduct from your prepaid credit, protecting your budget during unexpected downtime or malformed requests.
Unlock your key in minutes
Sign up, retrieve your key, and update the base URL. Simple as that.
