Generating a script for a 30-second voiceover
A prompt of 500 tokens costs $0.000125. The model generates 800 tokens at $0.000800. Total cost: $0.000925.
Xtts: Pay per token
Our text API uses simple, transparent rates: $0.15 per million input tokens and $0.50 per million output tokens. You only pay for actual usage, and your balance never drops below zero.
Top-ups from $20 to $500, any whole amount. Bonus credit: +5% from $50, +10% from $100, +15% from $200.
$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute
Cost calculator
Worked examples
Post-processing a 10,000-word transcript
Inputting a 12,000-token transcript costs $0.0030. Extracting structured JSON via 2,000 output tokens costs $0.0020. Total cost: $0.0050.
High-volume caption generation
Processing 50,000 input tokens for context costs $0.0125. Generating 15,000 tokens of output costs $0.0150. Total cost: $0.0275.
Token Rates
Our API charges strictly on token volume. Input tokens (your prompt) are priced at $0.15 per 1M tokens. Output tokens (the model's response) are priced at $0.50 per 1M tokens. There are no hidden fees, no per-request charges, and no tiered pricing. You pay exactly for the compute consumed by the uncensored model.
Crypto Payments
We support top-ups by crypto (USDT on TRC20, USDC on Base) in any whole amount between $20 and $500. Payments are processed instantly, and your credit balance updates immediately. This streamlined approach keeps our overhead low and ensures you get the best rate per token.
Bonus Credits
We reward larger deposits with bonus credit. Deposits of $50 or more receive a 5% bonus, while deposits of $100 or more receive a 10% bonus. This bonus credit is added to your balance and can be used for standard API requests. There is no expiration on your prepaid credit, so you can use your bonus whenever you are ready to scale your pipeline.
Free Errors & Refusals
If your request results in an error or hits a content refusal (such as the hard limit on sexual content involving minors), you are not charged. Errors are free. This means you only pay for successful completions. Combined with our prepaid model, you never overspend because your balance cannot go below zero, and you are never billed for failed requests.
Plan details
One price list, one set of limits, all features on every key.
| Item | Value |
|---|---|
| Context window | 100,000 tokens, input and output combined |
| Function calling | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| JSON mode | JSON object mode via response_format json_object |
| Max output | prompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap |
| Parallel requests | 8 requests at the same time per key |
| Rate limit | 300 requests per minute per key |
| Volume bonus | +5% on $50+, +10% on $100+, +15% on $200+ |
| Payment | crypto: USDT on TRON or USDC on Base, $20–$500, any whole sum |
| Token prices | $0.15 per 1M input tokens · $0.50 per 1M output tokens |
| Trial credit | $0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up |
| Subscription | no monthly fee; paid credit does not expire |
Questions and answers
Do I need a credit card to start?
No. You can sign up with Google or email and receive $0.50 in trial credit. Claim this credit with one click on your API key page. No card is required. For ongoing use, you can top up by crypto (USDT on TRC20, USDC on Base).
Does my prepaid credit expire?
No. Your prepaid credit never expires. You can top up once and use the balance over months or years. Bonus credits from top-ups are also subject to this same no-expiration policy.
What happens if I get double-charged?
Credit is not refunded automatically, but if you experience a billing error like a double charge, you can report it via the Support page. We will fix the issue and adjust your balance accordingly.
Why is output more expensive than input?
Generating text requires more compute power than processing input. Our pricing reflects this: input is $0.15/1M tokens, while output is $0.50/1M tokens. This is standard for uncensored LLMs running on dedicated hardware.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
