Together AI has announced a strategic partnership with Moonshot AI to serve as the launch platform for Moonshot's open-weight models, starting with Kimi K3. This collaboration provides developers with day-zero access to frontier releases through Together AI’s US-hosted infrastructure and tooling.
Kimi K3 is a 2.8T parameter sparse Mixture-of-Experts model featuring native vision support and a 1M token context window. It utilizes Kimi Delta Attention and Attention Residuals to achieve roughly 2.5x better scaling efficiency compared to Kimi K2. The models are available via Together AI's Serverless, Provisioned Throughput, and Dedicated Inference products.
Developers can post-train these models using custom training options like LoRA reinforcement learning and supervised fine-tuning. This integration allows for seamless deployment from experimentation to production without separate handoffs or SDK changes.