Open Source LLM API: Simple Pay-As-You-Go Pricing
We charge strictly for what you use: $0.25 per million input tokens and $1.00 per million output tokens. There are no subscriptions, monthly fees, or hidden costs—just simple pay-as-you-go pricing for your uncensored LLM API needs.
Worked examples
Batch processing 50,000 short summaries
Input: 5,000,000 tokens ($0.25 * 5 = $1.25). Output: 500,000 tokens ($1.00 * 0.5 = $0.50). Total cost: $1.75.
Long-context document analysis
Input: 30,000,000 tokens ($0.25 * 30 = $7.50). Output: 2,000,000 tokens ($1.00 * 2 = $2.00). Total cost: $9.50.
Interactive chat session
Input: 1,000,000 tokens ($0.25 * 1 = $0.25). Output: 500,000 tokens ($1.00 * 0.5 = $0.50). Total cost: $0.75.
Per-Token Rates
Our llm api pricing is based entirely on token consumption. You pay $0.25 for every 1 million input tokens and $1.00 for every 1 million output tokens. This structure applies to all requests, whether you are using the official OpenAI SDK or any other compatible client. Unlike some providers that charge differently for streaming or tool-use, our rates remain consistent. This transparency allows you to calculate exact costs per request based on your prompt and completion lengths. We do not charge for idle time or connection holds. You only pay for the tokens processed by the model, ensuring you are not billed for infrastructure you do not use.No Hidden Fees
When you integrate an open source llm api for inference, you expect the price you see to be the price you pay. We do not add surcharges for request volume, concurrent connections, or specific endpoint usage. The rate is uniform across all text generation tasks. Whether you are sending small prompts or large context windows, the per-token cost remains the same. There are no monthly platform fees or minimum spend requirements. If you send a request that results in zero output tokens due to an error, you are typically still charged for the input tokens processed, as that is the compute resource consumed. This clarity helps you budget accurately without worrying about surprise charges at the end of the billing cycle.Prepaid Credits Never Expire
We operate on a prepaid credit model. You load funds into your account, and those credits are used to pay for your API usage. A key benefit of this system is that your prepaid credits never expire. You can load funds today and use them weeks or months later without losing your balance. This is ideal for developers who may have bursty usage patterns or who prefer to manage their own cash flow. You can top up as little as $10, and we offer bonus credits for larger deposits. Since your balance is prepaid, your spending is strictly capped by your available credits, preventing unexpected overages.
Limits and what is included
Same price for every feature — function calling and JSON mode cost nothing extra.
| Feature | Support |
|---|---|
| Completion length | 16,000 tokens max; 2,048 if max_tokens is not set |
| Max context | 64,000 tokens, input and output combined |
| JSON mode | response_format: {"type": "json_object"} |
| Function calling | Supported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages |
| Concurrency | 8 requests at the same time per key |
| Rate limit | 300 requests per minute per key |
| Free trial | $0.50 of credit valid 7 days, no card needed |
| Subscription | no monthly fee; paid credit does not expire |
| Top-up | USDT (TRC20) or USDC (Base), any whole amount from $10 to $500 |
| Price | $0.25 per 1M input tokens · $1.00 per 1M output tokens |
| Volume bonus | +5% from $50, +10% from $100 |
Questions and answers
Do I need a credit card to start?
No. You can sign up with just an email and password to receive $0.50 in trial credits valid for 7 days. No card is required to begin testing the API.
Are bonus credits refundable?
The fact sheet does not specify refund policies for bonus credits. Base prepaid credits are yours to use, but you should review the specific terms during top-up to understand how bonus credits are applied.
Is this pricing similar to DeepSeek API or Groq API?
Our pricing is distinct. While other providers like DeepSeek or Groq have their own rates, we charge $0.25/1M input and $1.00/1M output. Always check the respective vendor's documentation for their current rates, as ours are independent.
What happens if I run out of credits?
Requests will fail until you add more funds to your account. Since we use a prepaid model, you cannot go into debt or incur charges beyond your loaded balance.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Get API key