Whisper API: Pay per token
Transparent, pay-as-you-go pricing for our uncensored text API. No monthly fees, no hidden costs, and prepaid credits never expire.
- $0.25per 1M input tokens
- $1.00Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
No subscription. Prepaid credit never expires.
Cost calculator
Worked examples
Post-processing a 20,000-token speech-to-text transcript
Input: 20,000 tokens. Output: 1,000 tokens. Cost: (20,000/1,000,000 * $0.25) + (1,000/1,000,000 * $1.00) = $0.005 + $0.001 = $0.006.
Generating captions for a short video clip
Input: 5,000 tokens (context/prompt). Output: 2,000 tokens (captions). Cost: (5,000/1,000,000 * $0.25) + (2,000/1,000,000 * $1.00) = $0.00125 + $0.002 = $0.00325.
Extracting structured data from a large document
Input: 50,000 tokens. Output: 10,000 tokens. Cost: (50,000/1,000,000 * $0.25) + (10,000/1,000,000 * $1.00) = $0.0125 + $0.01 = $0.0225.
Token Rates
We charge strictly per token processed. Input tokens cost $0.25 per 1M, and output tokens cost $1.00 per 1M. This flat rate applies to all requests, regardless of volume. There are no tiered pricing structures or volume discounts to negotiate. You pay exactly for what you consume, making it easy to predict costs for high-context pipelines.
Top-Up Bonuses
Prepaid credits are our only currency. We reward larger deposits with bonus credit. Top-ups start at $10. When you add $50, you receive a +5% bonus in credit. For a $100 top-up, the bonus increases to +10%. These bonuses are applied immediately to your account balance and can be used for any request type.
No Expiration & Predictable Spend
Your prepaid credits never expire, even if you pause your pipeline for weeks. This eliminates the risk of paying for unused monthly subscriptions. Because you pay upfront, your usage can never exceed your loaded balance, providing strict cost control. Note that while there are no monthly caps, each API key is limited to 300 requests per minute and an 8 MB request body size.
Limits and what is included
No tiers: every key gets the full feature set and the same limits.
| Spec | Value |
|---|---|
| Max context | 100,000 tokens, input and output combined |
| JSON mode | response_format: {"type": "json_object"} |
| Function calling | Yes — tools, tool_choice; replies carry tool_calls, also when streaming; send results back as role: tool |
| Max output | 16,000 tokens max; 2,048 if max_tokens is not set |
| Concurrency | 8 requests at the same time per key |
| Rate limit | 300 requests per minute per key |
| Trial credit | $0.50 for 7 days, no card |
| Subscription | paid credit never expires, no subscription |
| Bonus credit | +5% from $50, +10% from $100 |
| Token prices | input $0.25 / 1M tokens, output $1.00 / 1M tokens |
| Payment | crypto: USDT on TRON or USDC on Base, $10–$500, any whole sum |
Questions and answers
Do you charge for failed requests?
Yes, we charge for tokens processed in failed requests if they were successfully sent to the model. If the request fails before token processing begins (e.g., due to a 400 error), you are not charged.
Can I mix different models?
Currently, we offer a single uncensored large language model for all text completions. You will use the same model for all input and output, ensuring consistent behavior and pricing across your pipeline.
How do I check my remaining balance?
You can view your current balance and usage history in your account dashboard. API keys can be regenerated at any time, which revokes the old key but preserves your credit balance.
Is there a limit on how much I can spend?
There is no limit on your total spend, but each API key is rate-limited to 300 requests per minute. You can generate additional keys if you need higher throughput, and all keys share the same account balance.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
