Google Updates Gemini API Pricing with Tiered Charges Based on Inference Usage
2 day ago / Read about 0 minute
Author:小编   

Google has recently updated the billing plan for the Gemini API, with the new plan setting prices based on actual inference needs. The newly added inference services include standard, elastic, priority, batch, and cached versions. Among them, elastic inference utilizes idle computing power during off-peak hours, offering prices at a 50% discount, with a target delay of 1 to 15 minutes, though delay is not guaranteed. The batch API also enjoys a 50% discount, with delays of up to 24 hours.