Which AI model has the lowest cost per token?
Leiolai 1 Research Fast costs $0.01 per million input tokens and $0.02 per million output tokens at launch pricing. Input is the material you send to Leiolai; output is the response Leiolai writes. At these rates, one million input tokens plus one million output tokens costs $0.03.
Which AI API has the cheapest output tokens?
Leiolai 1 Research Fast charges $0.02 per million output tokens at launch pricing. At the same setting, Leiolai API input costs $0.01 per million tokens.
Compare token pricesWhich Leiolai setting uses these token prices?
Choose Research Fast when using Leiolai 1 through the API. The model stays Leiolai 1; higher thinking levels and Private mode have different token rates. The pricing table lists input and output rates for each setting.
See current Leiolai API pricingWhat does input plus output cost for a request?
Calculate the input and output charges separately. At Leiolai Research Fast launch rates, one million input tokens costs $0.01 and one million output tokens costs $0.02, for $0.03 combined. Your selected mode and effort determine the rates used.
Is API pricing the same as an app subscription?
Leiolai API requests are billed by tokens. The Leiolai app also offers Free and paid memberships with their own usage limits and earning bonuses. Compare API rates for an integration and app plans for everyday chat.
Free and paid app accessHow much would 100,000 input tokens and 2,000 output tokens cost?
At Leiolai Research low launch rates, that request costs $0.00104: $0.001 for the input and $0.00004 for the output. Calculate each side using its own rate, then add the two amounts. The selected mode and effort must match the rate used.
Do all thinking levels use the lowest token rates?
Leiolai Research low uses the quoted $0.01 input and $0.02 output rates per million tokens. Medium, high, and xhigh have different rates, and Private has its own table. Choose the mode and effort before comparing a request’s cost.
Choose effort Compare the complete rate tableWhat matters when comparing the cost of AI APIs?
Count both sides of the request: input tokens sent to Leiolai and output tokens generated in response. Include any conversation history or documents your client sends with the new message. Then apply the input and output rates for the mode and effort you selected.
Can I read the usage that was billed for a request?
When returned, usage counts report the input and output tokens used for billing. Leiolai Chat Completions streams need stream_options.include_usage: true for the final usage chunk. Keep the counts with the mode and effort used for the request.
Read token usage