Together AI at NVIDIA GTC 2026: Explore our latest innovations across research and products

2026-06-09 · Source: Together AI | The AI Native Cloud - Together.ai · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Software Development & Engineering · Depth: Advanced, short

Summary

Together AI is showcasing its latest innovations at NVIDIA GTC 2026 from March 16–19, focusing on making AI systems more open, agentic, and production-ready. Key announcements include the integration of NVIDIA Dynamo 1.0, an open-source software for generative and agentic inference, into Together AI's inference stack for optimized performance. The company is also collaborating on NVIDIA NemoClaw, an open-source stack simplifying OpenClaw assistant deployment, and hosts the NVIDIA OpenShell runtime, offering access to over 150 optimized models for high-performance inference. Additionally, Together AI supports NVIDIA Nemotron 3 Super, a 120B total parameter (12B active per token) hybrid mixture-of-experts model with a 1M-token context window for multi-agent workflows, deployable via its Dedicated Model Inference. The NVIDIA Parakeet TDT 0.6B V3 ASR model is also now available in the Together AI Model Library for real-time voice applications.

Key takeaway

For AI Engineers building agentic systems or requiring high-performance inference, Together AI's new NVIDIA integrations offer critical tools. You can now leverage NVIDIA Nemotron 3 Super for complex multi-agent workflows or deploy Parakeet TDT 0.6B V3 for real-time voice agents. Explore Together AI's dedicated endpoints and model library, accessible via NemoClaw, to achieve production-scale speed and cost efficiency for your AI-native applications.

Key insights

Together AI and NVIDIA are advancing open, agentic, and production-ready AI systems through new model integrations and inference optimizations.

Principles

• AI systems are evolving towards openness and agentic capabilities.
• Production AI requires high performance and cost-efficiency.
• Hybrid model architectures can optimize multi-agent workflows.

In practice

• Deploy Nemotron 3 Super for multi-agent workflows.
• Build real-time voice agents with Parakeet TDT 0.6B V3.
• Access 150+ optimized models via NemoClaw.

Topics

• NVIDIA GTC 2026
• Agentic AI
• LLM Inference
• NVIDIA Dynamo 1.0
• NVIDIA Nemotron 3 Super
• Voice AI

Best for: Machine Learning Engineer, NLP Engineer, CTO, AI Engineer, MLOps Engineer, AI Scientist

Related on AIssential

• Together AI Brings NVIDIA Nemotron 3 Nano Omni to Developers on Day 0 — NVIDIA Nemotron 3 Nano Omni unifies multimodal reasoning in a single, open model, enhancing agentic AI efficiency and capability.
• Nvidia's big AI day at GTC — Nvidia's GTC 2026 unveiled significant advancements, including the NemoClaw security stack for OpenClaw agents, the next-gen Vera Rubin platform with seven new AI chips, and DLSS 5 for photorealistic…
• LWiAI Podcast #237 - Nemotron 3 Super, xAI reborn, Anthropic Lawsuit, Research! — The AI landscape is rapidly evolving with new agentic tools, model releases, market shifts, and critical policy and research challenges.
• NVIDIA Jetson Brings Agentic AI to the Physical World — NVIDIA Jetson now supports agentic AI via JetPack 7.2 and NemoClaw, enabling physical AI agents at the edge.
• Develop Native Multimodal Agents with Qwen3.5 VLM Using NVIDIA GPU-Accelerated Endpoints — Qwen3.5 is a ~400B parameter open-source VLM with a hybrid MoE and Gated Delta Network architecture, excelling in UI navigation.
• Nemotron 3: NVIDIA’s Latest LLM in Plain English — Nemotron 3 balances advanced AI capabilities with practical deployment efficiency for agentic workloads.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Together AI | The AI Native Cloud - Together.ai.