Today we're shipping Prism: a new option in the Augment model picker that efficiently routes each turn to the model that fits the work. On our internal multi-turn coding benchmark, Prism matches the best individual model on quality at 20–30% lower cost per task than frontier models.

Token usage is exploding, and so is cost. The best models deliver undoubtedly superior quality, but all tasks are not created equal. For simple tasks, using the SOTA reasoning model is like driving a Ferrari to go 4 blocks to the grocery store. Prism is a meaningful cost decrease: teams sending 10,000 user messages a month can expect to save $20,000 on their token spend, at similar or better quality.

We know 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. → Prism (GPT + Kimi) targets GPT 5.5 → Prism (Claude + Gemini) targets Opus 4.7

Building a model router is non-trivial. The hard part isn't picking - it's switching. Prism's job is to switch only when the expected win from a different model exceeds the cost of the cache eviction.

Augment can do this because we are model agnostic. No single model wins every task, so we give our customers access to all the industry leaders. That's the foundation Prism is built on: a pool of frontier models, with the routing decision made per turn rather than at the start of a session.