Hermes API: Token pricing
Transparent token pricing for the Hermes API ensures you know exactly what your requests cost before you send them. With prepaid credits that never expire, your spending remains fully predictable and under your control.
- per 1M input tokens
- $0.25
- Output tokens / 1M
- $1.00
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
No subscription. Prepaid credit never expires.
Cost calculator
Worked examples
Standard code generation task
A prompt of 1,000 tokens generates 500 tokens of code. Input cost: 0.001 * 0.25 = $0.00025. Output cost: 0.0005 * 1.00 = $0.0005. Total per request: $0.00075.
Long-context document analysis
Processing a 10,000-token document with a 2,000-token summary output. Input cost: 0.01 * 0.25 = $0.0025. Output cost: 0.002 * 1.00 = $0.002. Total: $0.0045 per document.
Batch processing of short queries
Sending 20 requests, each with 500 input tokens and 300 output tokens. Input: 0.0005 * 0.25 = $0.000125. Output: 0.0003 * 1.00 = $0.0003. Total per request: $0.000425. Batch total: $0.0085.
Token Pricing Rates
The Hermes API charges based on the volume of tokens processed. Input tokens are priced at $0.25 per million tokens, while output tokens cost $1.00 per million tokens. This structure reflects the higher computational cost of generating text compared to processing it. These rates apply to the single uncensored model available via our endpoint. Unlike complex routing services, there are no hidden fees for model selection or version changes. You can estimate your costs precisely using the calculator above. This transparency allows you to budget accurately for high-volume workloads without worrying about variable pricing tiers. The pricing is consistent regardless of the client SDK you use, provided it is OpenAI-compatible.
Prepaid Credit & Bonuses
We operate on a prepaid credit system with no monthly subscriptions. You top up your account using crypto (USDT or USDC). Bonus credits are added automatically to encourage larger deposits. Adding $50 in credit grants a 5% bonus, while $100 in credit provides a 10% bonus. These bonuses are added to your available balance and can be used for standard API requests. There is no expiration date for your prepaid credits, so you can top up when it suits your budget. This model eliminates the risk of unexpected charges after your trial ends. You always know exactly how much you have spent and how much remains available for future requests.
No Expiration Policy
Your prepaid credits never expire, regardless of how long you wait to use them. This policy benefits developers who run sporadic workloads or test the API occasionally. You can top up once and use the balance over months or years without losing funds. This contrasts with services that charge monthly fees or require constant renewal. The only limit is the 300 requests per minute rate limit per key. Your balance remains available until you choose to spend it. This approach provides financial predictability and reduces administrative overhead. You do not need to track billing cycles or worry about service interruptions due to payment lapses.
Payment Methods
We accept major crypto (USDT or USDC) for top-ups. Minimum top-up amounts start at $10, making it easy to start with a small budget. New accounts receive $0.50 in trial credit valid for 7 days, requiring no payment method. This allows you to test the API before committing to a larger deposit. All transactions are processed securely. Once you top up, the credit is immediately available in your account. You can view your balance and usage history in your dashboard. The prepaid model ensures that your usage can never exceed the amount you have loaded. This prevents surprise bills and keeps your costs strictly under your control.
Plan details
No tiers: every key gets the full feature set and the same limits.
| Parameter | Details |
|---|---|
| Completion length | up to 16,000 tokens per request (default 2,048) |
| Tools / tool calls | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| Structured output | JSON object mode via response_format json_object |
| Max context | 100,000 tokens (prompt + completion together) |
| Parallel requests | 8 requests at the same time per key |
| Rate limit | 300 requests per minute per key |
| Bonus credit | +5% on $50+, +10% on $100+ |
| Top-up | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Credit expiry | no monthly fee; paid credit does not expire |
| Free trial | $0.50 of credit valid 7 days, no card needed |
| Token prices | $0.25 per 1M input tokens · $1.00 per 1M output tokens |
Questions and answers
Do I need a credit card to start?
No, you can sign up with just an email and password. New accounts receive $0.50 in trial credit valid for 7 days, allowing you to test the API immediately without entering payment details.
What happens to my credits if I stop using the API?
Your prepaid credits never expire. You can top up once and use the balance whenever you need it, whether that is next week or next year. There are no monthly fees or usage deadlines.
Are there any hidden fees or per-request charges?
No. You only pay for the tokens processed. There are no additional fees for streaming, tool calling, or standard API features. The rates are fixed per million tokens for input and output.
Can I mix prepaid credits with other billing methods?
We currently operate on a prepaid model only. There is no post-bill or credit card charge-after-use option. You must load credits into your account before sending requests, ensuring your spend never exceeds your balance.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
