Transparent uncensored API pricing
You pay only for the tokens your model actually uses at direct base rates, with no hidden routing fees or monthly subscriptions. Our transparent API pricing ensures your budget matches your usage exactly.
No subscriptions. Prepaid credits do not expire.
- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Cost estimator
Usage examples
A nightly batch job processing 50,000 short user reviews for sentiment analysis.
Input: 50,000 tokens. Output: 5,000 tokens (summaries). Input cost: 50,000 / 1,000,000 × $0.15 = $0.0075. Output cost: 5,000 / 1,000,000 × $0.50 = $0.0025. Total: $0.01.
A single complex coding task requiring a large context window and detailed explanation.
Input: 80,000 tokens (code context). Output: 2,000 tokens (solution). Input cost: 80,000 / 1,000,000 × $0.15 = $0.012. Output cost: 2,000 / 1,000,000 × $0.50 = $0.001. Total: $0.013.
A streaming chat session with moderate back-and-forth conversation.
Input: 10,000 tokens. Output: 4,000 tokens. Input cost: 10,000 / 1,000,000 × $0.15 = $0.0015. Output cost: 4,000 / 1,000,000 × $0.50 = $0.002. Total: $0.0035.
Per-token pricing breakdown
The uncensored LLM charges $0.15 per million input tokens and $0.50 per million output tokens. This structure reflects the computational difference between processing your context and generating new text. You do not pay for the model selection overhead that typical aggregators add. Our cost is strictly tied to the tokens you send and receive. Errors or refusals consume zero credits. This direct model ensures your API pricing matches the actual work performed.
Prepaid credit and bonuses
Load your account with crypto to receive bonus credit on your balance. Top-ups start at $20 and go up to $500. You receive a 5% bonus for deposits of $50, 10% for $100, and 15% for $200. This prepaid system keeps your spending predictable without monthly commitments. Your credit never expires, so you can use it whenever you need processing power. Start with a free trial to verify the integration works with your stack.
Why prepaid credit works best
A prepaid balance prevents unexpected bills from runaway loops or high-volume jobs. You control exactly how much compute you purchase before you start. Since we do not route through multiple vendors, there are no hidden markups on the token rate. Your data stays in a compliant environment without complex billing cycles. You simply top up when the balance runs low. This approach aligns costs directly with your application's usage patterns.
Common questions
Is this the cheapest openrouter pricing available?
We offer base rates without the typical aggregator markup. While some vendors may list lower raw rates, our transparent pricing includes no hidden fees. You pay exactly what the tokens cost plus any applicable bonus credit.
Do I pay for failed requests?
No. If a request fails or returns an error, those tokens are not charged. You only pay for successful token generation and processing. This ensures you are not penalized for network issues or invalid parameters.
How do I calculate my costs accurately?
Multiply input tokens by 0.00000015 and output tokens by 0.00000050. Sum these values to get the total cost in USD. Our system tracks this automatically so you never have to guess your spend.
Does the prepaid credit expire?
Your prepaid credit never expires. You can load it once and use it over months or years. This is ideal for projects with irregular traffic patterns. You retain full control over your funds until you choose to spend them.
Get your API key
Register, copy the key, update your base URL. That is the complete configuration.
