Google updates Gemini API pricing, charging based on inference usage tiers

MarsBitNews · 2026-04-03T06:53:37+00:00

Google has updated the billing tiers for the Gemini API, adding Standard, Flexible, Priority, Batch, and Cache versions, offering different latency and discounts, and optimizing inference services to meet diverse needs. The Flexible and Batch tiers both have a 50% discount; the Priority tier is priced higher but offers lower latency, suitable for real-time applications.

MarsBitNews

2026-04-03 06:53:37

Abstract generation in progress

Mars Finance news. On April 3, Google recently updated the billing tiers for the Gemini API, with both the optimization scheme and pricing set based on actual inference usage needs. The newly added inference service tiers include: Standard, Flex, Priority, Batch, and Caching. Among them, the Flex inference tier takes advantage of off-peak idle computing resources to provide a 50% discount on the standard price, with a target latency of 1 to 15 minutes, but no latency guarantee. The Batch API tier likewise offers a 50% discount on the standard rate, with latency that can be up to 24 hours. The Caching tier is billed based on the number of cached tokens and the storage duration, and is recommended for scenarios such as dialogue robots deployed with complex system instructions, repeated analysis of long video files, and large-scale document set queries. The Priority tier is priced 75% to 100% higher than the standard price, with latency controllable at the millisecond-to-second level. Google recommends this tier for scenarios such as real-time customer service chatbots, real-time fraud detection, and business-critical intelligent assistants. (Wide-angle observation)

View Original

This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.

2 Likes