Pricing: Pay Per Token for Uncensored LLM

Transparent Token Pricing

The API charges $0.15 per million input tokens and $0.50 per million output tokens. You pay exactly what you consume, with no minimum monthly commitments. Errors and refusals do not consume your credit. This model eliminates the waste of flat-rate subscriptions when traffic fluctuates.

Unrestricted AI models often require heavy context windows. Our pricing scales linearly with your usage. High-volume developers can predict costs accurately because the rate per token remains constant regardless of volume. There are no tiered discounts or sudden price hikes after a certain threshold.

Every request is billed based on actual token counts. Short prompts with long responses cost more than long prompts with short answers. This reflects the compute load accurately. You retain full control over your spend by setting max_tokens in your requests.

Crypto Top-Up and Bonus Credits

Credit is topped up exclusively via USDT (TRC20) or USDC (Base). Any whole amount between $20 and $500 is accepted. This ensures fast settlement and lower fees for global developers. Bonus credit is added automatically: +5% for $50, +10% for $100, and +15% for $200.

Your prepaid balance never expires. You can top up whenever you want, even with small amounts. The bonus structure rewards larger deposits without locking you into a subscription. Errors are free, so your credit lasts longer than expected. This prepaid model keeps your budget predictable and avoids surprise charges.

Sign up with Google or email to get your API key. The key is shown immediately. No phone number is required. You can mix and match top-up amounts as your project grows.

Request Limits and Quotas

Each API key supports 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. These limits are designed for steady, reliable usage without overwhelming the servers. If you need higher concurrency, consider using multiple API keys. Each account allows one active key at a time; a new key replaces the old one.

The context window is 100,000 tokens, with no separate output cap. If you do not set max_tokens, the response can run to the end of the window. These limits ensure fair usage for all developers. Streaming via SSE is supported, allowing real-time token delivery. Function calling and JSON mode are also available.

Requests are processed in order of arrival. If you hit the rate limit, you will receive an error response. Errors do not consume your credit. This allows you to retry requests without penalty. The 8 MB body limit accommodates large JSON payloads with many tools or messages.