Transparent llm api pricing and billing

Transparent LLM API pricing and billing

We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free, so you only pay for successful inference. This structure keeps your costs predictable regardless of volume. You can scale from a few requests to millions without hitting tiered limits or hidden fees. The prepaid credit model ensures you never overspend. Your balance decreases only when the model generates tokens. This approach removes the complexity of subscription tiers. You get raw inference efficiency without vendor lock-in. Check our docs for integration details.

Prepaid credit and expiration

Your prepaid credit never expires, so you can top up whenever convenient. We charge by real token usage, meaning unused balance stays in your account indefinitely. This eliminates the risk of losing monthly credits. You can monitor your usage in real-time through the API response headers. Errors do not consume credit, which further reduces your effective cost. You can also start with a free trial. Every new account receives $0.50 of trial credit valid for 7 days.

Why prepaid keeps spend predictable

A prepaid balance acts as a hard cap on your spending. You cannot exceed your credit amount, which prevents surprise overages. This is crucial for projects with strict budget constraints. You can run cost calculators based on our token rates to forecast monthly expenses accurately. The lack of minimum spend requirements means even small projects remain viable. You avoid the waste of unused subscription tiers. Your focus stays on building features rather than managing billing cycles. This model aligns our incentives with your actual usage patterns.