Get API Key
Create an account to receive your API key instantly. No credit card is required to start testing the uncensored LLM with trial credit.
Your API key
Keep this key secret. Anyone who has it can spend your credit.
Base URL:
Model:
Balance: $
Requests:
Crypto top-ups (USDT, USDC) are available on this site. Until then your trial credit applies.
No Credit Card Needed
Sign up with just an email and password to receive $0.50 in trial credit valid for 7 days, allowing immediate testing without financial commitment.
Instant Key Generation
Your API key is displayed immediately upon signup, ready to be pasted into your preferred OpenAI-compatible client or SDK without waiting for approval.
Single Key, Full Control
Manage your access with one key per account that can be regenerated at any time to revoke access instantly if credentials are exposed.
Start Coding Now
Use standard OpenAI SDKs to send requests to the uncensored model and receive text responses, tool calls, or streaming outputs without friction.
How it works
Create Account
Enter your email and create a password on the signup form to register your account.
Get Your Key
Receive your unique API key instantly on the confirmation screen for immediate use.
Integrate & Test
Paste the key and the base URL into your client to make your first request to the uncensored AI models.
Access Raw Output Without Guardrails
With your API key, you gain direct access to a single, truly uncensored large language model hosted on our GPU servers. This is not an aggregation of various vendors' models; it is one specific open-weight model tuned to answer without content refusals for lawful adult use, including controversial or explicit topics. You can send text and receive text, supporting both standard responses and streaming via Server-Sent Events. The API follows the standard OpenAI chat-completions format, meaning you can use the official OpenAI SDKs or any compatible client. You get full control over your requests, with a 100,000 token context window and support for tool/function calling. There is no model routing or complex configuration; you send a request to https://api.uncensoredaimodels.com/v1 and receive raw output tailored for power users who want to integrate uncensored capabilities directly into their applications.
Transparent Billing and Trial Terms
Your trial account comes with $0.50 of credit that expires after 7 days, requiring no credit card to start. When you are ready to scale, you can top up your prepaid balance starting at $10 using crypto (USDT or USDC). The credit never expires, and we apply bonus credits automatically when you reach certain thresholds: you receive a 5% bonus when topping up $50 or more, and a 10% bonus when topping up $100 or more. There are no monthly subscriptions or hidden fees. Pricing is set at $0.25 per 1 million input tokens and $1.00 per 1 million output tokens. Your prompts are not used for training, and the only hard content limit is that sexual content involving minors is always blocked.
Questions and answers
Is a credit card needed to sign up?
No, you only need an email address and a password to create an account. You will receive $0.50 in trial credit immediately, which is valid for 7 days. You do not need to enter payment details until you choose to top up your prepaid balance for continued usage.
What happens when my trial credit runs out?
Your trial credit expires after 7 days regardless of usage. Once it is gone, you will need to top up your account with at least $10 to continue making requests. You can pay via crypto (USDT or USDC), and the credit you add will never expire.
How do I replace a leaked API key?
You can regenerate your API key at any time from your account settings. When you generate a new key, the previous one is immediately revoked, ensuring that anyone with the old key can no longer access your account or use your credits.
What are the limits on the uncensored API?
You are limited to 300 requests per minute per key, with a maximum request body size of 8 MB. Each account is limited to one key, which you can regenerate if needed. The model supports up to 100,000 tokens for the combined prompt and completion.
