News

Together AI
together. ai > blog > together-ai-partners-with-pearl-research-labs

Together AI and Pearl Research Labs Team Up to Reduce the Cost of AI Inference

6+ hour, 22+ min ago  (243+ words) " Flash Attention-4: up to 1. 3" faster than cu DNN on NVIDIA Blackwell " Introducing Together AI's new look " " ATLAS: runtime-learning accelerators delivering up to 4x faster LLM inference " Together GPU Clusters: self-service NVIDIA GPUs, now generally available " " Batch Inference API: Process billions of…...

Together AI
together. ai > customers > decagon

How Decagon Engineered Sub-Second Voice AI with Together AI

2+ mon, 3+ week ago  (685+ words) API for inference on open-source models Deploy models on custom hardware Scalable infra for generative media Train & improve high-quality, fast models Chat app for open-source AI Which LLM to Use Find the "right" model for your use case Clusters of…...

Together AI
together. ai > models > minimax-m2-5

Mini Max M2. 5 API

3+ mon, 1+ day ago  (245+ words) API for inference on open-source models Deploy models on custom hardware Scalable infra for generative media Train & improve high-quality, fast models Chat app for open-source AI Which LLM to Use Find the "right" model for your use case Clusters of…...