Together AI brings Moonshot’s Kimi K3 online with 1M context and agent tools
togethercompute · x · 2026-07-28
Together AI says Kimi K3 is now live as a day-one launch partner for Moonshot’s open frontier model.
The model is positioned for long-running agentic workloads across code, tools, vision and research. The launch materials highlight:
- 2.8T total parameters with 16 of 896 experts active per token
- 1M context window
- native vision for screenshot-guided coding
- repository navigation and terminal tool use
- complex research and knowledge workflows
Together also frames itself as an efficient production path for long, tool-heavy agent tasks, hosted on U.S.-based infrastructure with zero data retention.
Related event: Moonshot's Kimi K3 Flagship Model Launches on Together AI(12 posts)→
More from coding & agent
- Model Is the Least Interesting Part: A Guide to Six Core AI Architectures from RAG to Multi-Agent — goyalshaliniuk · 2026-09-11
- Non-coder builds layered memory architecture: 20k tokens tracks a year of agent conversations — matteoianni · 2026-09-11
- Warp's six non-engineering teams all run on Linear and Claude Code — mon__lim · 2026-09-11
- 9-year backend dev: AI code isn't the problem, the rate of making a mess is — Sweaty-Landscape-561 · 2026-09-11
- RTK claims token savings, but our cost benchmarks disagree — michalwarda · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11