Back to AIBriefs
AnalysisDevelopers

DecagonAI cuts voice agent costs 6x with Together AI fine-tuned open models

Together AI
@togethercompute

Accelerate inference, model shaping, and pre-training on a research-optimized platform.

San Francisco, CAtogether.ai
View on X
Together AI avatar
Together AI
@togethercompute

.@DecagonAI cut voice agent cost per turn nearly 6x with Together AI. They moved from closed models to fine-tuned open models, while keeping latency low enough for real-time voice: → <400ms p95 model latency per turn → custom speculators and prompt caching → optimized

·
2 hours ago