What will your API requests cost?
Choose a catalog model and enter average tokens per request and monthly request volume. Compare an estimate in USD using the public input and output rates.
Estimate your usage.
The starting values are editable examples, not a forecast of your usage.
kimi-k3.1-pro-uncensored
Your estimate in USD
- Per request
- USD 0.00147
- Per month
- USD 14.70
Applied rates · USD per 1 million tokens
- Input
- USD 0.42
- Output
- USD 2.10
Text-token estimate at standard rates, without caching, paid tools or dedicated commercial terms. This calculator covers up to 100,000 input and 100,000 output tokens per request; actual limits depend on the model.
Check model pricing and detailsHow is the cost calculated?
Cost per request = (input tokens × input rate + output tokens × output rate) ÷ 1,000,000. Monthly cost multiplies this amount by the number of requests.
The calculation uses catalog values without rounding the rates first. It estimates usage cost, not a quote: actual charges depend on measured tokens and applicable conditions. Check model details for longer contexts, caching or special modes.
Which tokens should I count?
Input can include instructions, conversation history and tool results sent to the model. Output is what the model generates, including any billed reasoning tokens. Start with usage data from representative requests; an agent may make several requests for a single task.
Read the API referenceTurn the estimate into an integration.
Try the model on requests representative of your service. To resell the APIs, share your chosen models and expected volumes with the team to discuss a master key and dedicated rates.