Augment Code 官方最新动态:Introducing Augment Prism: model routing to reduce cost and maintain quality
来源:Augment Code 官方动态 | 发布日期:2026-05-02T18:42:50.293Z
核心更新概览
Prism is a new option in the Augment model picker that routes each user turn to whichever underlying model best fits the work. For a team sending 10,000 user requests per month, Prism translates to ro
详细内容记录
Prism is a new option in the Augment model picker that routes each user turn to whichever underlying model best fits the work. For a team sending 10,000 user requests per month, Prism translates to roughly $20,000 in monthly savings, or up to 30% lower cost, with a negligible quality difference compared to the frontier reasoning models it routes between. Select Prism in the picker to get frontier-model quality at lower cost. How Prism performs vs. frontier reasoning models Prism matches the best individual model in our comparison on quality, while costing about 20-30% less per task than frontier reasoning models. This data is based on our internal multi-turn coding benchmark, which better emulates real sessions with tasks of varying complexity than benchmarks like SWE bench and Terminal bench. (More on our methodology below). Two Prism configurations appear below: one tuned to match Opus 4.7's quality envelope at lower cost; and one aimed at matching GPT 5.5. We know from our customers that developers and teams have strong preferences for different model families: with Prism, you can stay in the model family you like, at lower cost. Opus 4.7, Sonnet 4.6, Gemini Flash 3.0 Each Prism configuration delivers the same quality range and lower cost per task as the model it's tuned to match. Each variant hits its design target on quality and is cheaper than the corresponding manual pick. That's the result a router should produce.
更多技术细节可访问官方原文:https://www.augmentcode.com/blog/augment-prism-model-routing-to-reduce-cost-and-maintain-quality。