EN ▾
Try with trial credit

Transparent Pay-As-You-Go Pricing

Transparent pay-as-you-go pricing means you pay only for the tokens your app actually consumes, with no hidden fees or monthly subscriptions. Our prepaid balance keeps spend predictable while supporting crypto top-ups for privacy-focused developers.

$0.15
per 1M input tokens
$0.50
Output tokens / 1M
100,000
token context
$0.50
trial credit
300
requests per minute

Pricing estimator

$0.00
Try with trial credit

Real-world usage

Short-form content generation

A script generating 100 responses with 500 input tokens and 200 output tokens each costs 0.00015 + 0.00010 = $0.00025 per response. For 1,000 responses, the total is $0.25. This demonstrates how low-volume usage remains cost-effective.

Long-context document analysis

Processing a 50,000 token document to extract 1,000 tokens of insights requires 50,000 input tokens and 1,000 output tokens. The cost is (50,000 / 1,000,000 * 0.15) + (1,000 / 1,000,000 * 0.50) = $0.0075 + $0.0005 = $0.008. High context windows do not drastically increase the per-request cost.

High-volume chatbot traffic

A chatbot handling 10,000 requests with 1,000 input tokens and 100 output tokens each uses 10,000,000 input tokens and 1,000,000 output tokens. The cost is (10,000,000 / 1,000,000 * 0.15) + (1,000,000 / 1,000,000 * 0.50) = $1.50 + $0.50 = $2.00. Scaling up remains affordable with prepaid credit.

Crypto Top-Up and Bonus Credit

Top-up your prepaid balance with USDT on TRC20 or USDC on Base. We accept whole amounts between $20 and $500, ensuring you get exactly the credit you need. Bonus credit rewards larger deposits: top up $50 or more for a 5% bonus, $100 or more for 10%, and $200 or more for 15%. This crypto-only approach maintains privacy for developers who prefer it. Errors and refusals do not consume your balance, so you only pay for successful completions. Your credit never expires, allowing you to top up when convenient.

Rate Limits and Request Constraints

Our API supports 300 requests per minute per key and allows 8 concurrent requests. Each request body must not exceed 8 MB. These limits ensure fair usage for all developers while maintaining high availability. If you need higher throughput, consider distributing requests across multiple API keys. Streaming via SSE is supported, allowing you to receive tokens as they are generated. Function calling, JSON mode, and standard parameters like temperature and top_p are available. The context window supports up to 100,000 tokens, with a maximum output of 16,000 tokens per request.

Free Trial and Refund Policy

Every new account receives $0.50 of trial credit valid for 7 days. Sign up with Google or email and password to receive your API key instantly. Your prepaid credit is not refunded, but it never expires. If you experience a double charge or error, use the Support page to resolve it. This policy ensures you can test the uncensored model without financial commitment. Errors and refusals are free, so your trial credit is only consumed by successful completions. This makes it easy to evaluate the API's performance before committing to a larger top-up.

Common questions

How does prepaid credit work with the unfiltered LLMs API?

Prepaid credit is charged based on real token usage, with errors and refusals being free. Your credit never expires, allowing you to top up when convenient. This model keeps spend predictable and eliminates monthly subscription fees.

What payment methods are accepted for top-ups?

We accept crypto only: USDT on TRC20 or USDC on Base. Minimum top-ups are $20, and maximums are $500. Bonus credit is added for larger deposits: 5% for $50+, 10% for $100+, and 15% for $200+.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

What are the rate limits for the API?

The API supports 300 requests per minute per key and allows 8 concurrent requests. Each request body must not exceed 8 MB. These limits ensure fair usage for all developers while maintaining high availability. If you need higher throughput, consider distributing requests across multiple API keys.

Get your API key now

Sign up, grab your key, point to the new base URL. You are ready to go.

Try with trial credit