Transparent LLM Proxy Pricing
Our llm proxy pricing is transparent and straightforward: pay only for the tokens you use with no hidden fees or subscription commitments. This openai compatible api model ensures your costs scale linearly with your actual inference volume.
No subscription. Prepaid credit never expires.
Cost calculator
Worked examples
Small-scale development testing
A developer runs 100 requests with an average of 2,000 input tokens and 500 output tokens per request. Total input: 200,000 tokens ($0.25 * 0.2 = $0.05). Total output: 50,000 tokens ($1.00 * 0.05 = $0.05). Total cost: $0.10.
Medium batch processing
An engineer processes a dataset of 10,000 documents. Each document averages 10,000 input tokens and 500 output tokens. Total input: 100,000,000 tokens ($0.25 * 100 = $25.00). Total output: 5,000,000 tokens ($1.00 * 5 = $5.00). Total cost: $30.00.
High-volume inference workload
A production app handles 1,000,000 requests. Average 500 input tokens and 200 output tokens per request. Total input: 500,000,000 tokens ($0.25 * 500 = $125.00). Total output: 200,000,000 tokens ($1.00 * 200 = $200.00). Total cost: $325.00.
Pay-As-You-Go Rates
We charge strictly per token consumed, with no monthly base fee. Input tokens cost $0.25 per million tokens, while output tokens are priced at $1.00 per million tokens. This structure reflects the higher computational cost of generating text compared to processing it. Because we operate as an independent llm proxy, these rates apply uniformly regardless of your volume. There are no tiered discounts or hidden egress fees. You can monitor your exact usage in real-time through the dashboard. This model works well for developers who prefer predictable per-unit costs over complex enterprise contracts. If you need a simple openrouter alternative for uncensored inference, this pricing model keeps your overhead low and your billing simple.
Top Up & Bonus Credits
Prepaid credit is the foundation of our billing system. When you top up, you add funds to your account balance. We offer bonus credits to reward larger deposits: a 5% bonus is applied to top-ups of $50 or more, and a 10% bonus is applied to top-ups of $100 or more. These bonuses are credited immediately and can be used for inference just like your base funds. The bonus credits do not expire, and they are consumed proportionally with your main balance. This mechanism allows you to reduce your effective cost per token while maintaining full flexibility. It is an efficient way to manage cash flow for your AI projects without locking you into a long-term commitment.
No Expiration
Your prepaid credit never expires. Whether you top up $10 or $1,000, the balance remains available until you use it. This is critical for projects with sporadic usage patterns or long-term archival needs. You do not need to worry about monthly renewals or service interruptions due to expired credits. The only limit is the 300 requests per minute rate limit per key. This permanence allows you to scale your llm proxy usage up or down without financial penalty. It also simplifies budgeting for engineering managers who want to avoid the administrative overhead of tracking subscription expiration dates.
Specs that affect cost
Same price for every feature — function calling and JSON mode cost nothing extra.
| Item | Value |
|---|---|
| Tools / tool calls | 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 |
| Max context | 100,000 tokens (prompt + completion together) |
| Structured output | JSON object mode via response_format json_object |
| Rate limit | 300/min per key |
| Parallel requests | 8 requests at the same time per key |
| Subscription | paid credit never expires, no subscription |
| Top-up | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Trial credit | $0.50 for 7 days, no card |
| Price | $0.25 per 1M input tokens · $1.00 per 1M output tokens |
| Bonus credit | +5% on $50+, +10% on $100+ |
Questions and answers
Do I need a credit card to start?
No. You can create an account with just an email and password. New accounts receive $0.50 in trial credit valid for 7 days, allowing you to test the API without entering payment details. You only need to add a payment method when your trial credit is exhausted or when you wish to make a top-up.
How are bonus credits consumed?
Bonus credits are consumed proportionally alongside your base credit. When a request is processed, a fraction of both your base funds and your bonus funds is used. This ensures that your bonus credits are utilized fairly and effectively over time. You do not need to manually select which credit type to use.
Is there a minimum top-up amount?
The minimum top-up amount is $10. You can pay using major crypto (USDT or USDC). Once the top-up is processed, your balance is updated immediately, and you can start making requests right away.
What happens if I exceed my balance?
Requests will fail if your balance is insufficient to cover the cost of the tokens. We recommend monitoring your usage through the dashboard to avoid unexpected interruptions. Since there is no subscription, you are not charged for failed requests, and you only pay for the tokens actually consumed.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
