Moonshot Releases and Open-Sources Kimi K3
heyshrutimishra · x · 2026-07-17
Moonshot has launched Kimi K3, branded as "Open Frontier Intelligence."
- The model features 2.8 trillion parameters, is natively multimodal, and supports a 1 million token context.
- The team claims it excels in long-context reasoning and agentic coding tasks, noting that Kimi Delta Attention can boost decoding speeds for million-token contexts by up to 6.3x.
- Training utilizes Attention Residuals, reportedly improving training efficiency by about 25% with an additional cost of less than 2%.
- The model is now available on the Kimi website, Kimi Work, Kimi Code, and via API.
- Open Weights are scheduled for release on 2026-07-27.
- External observations highlighted strong performance on benchmarks like SWE-Bench Pro, SWE-bench Multilingual, BrowseComp, and Toolathlon, alongside highly competitive inference pricing.
Related event: Kimi K3 Triggers a Reassessment of Chinese Frontier AI(94 posts)→
More from Models
- GPT 6.1 Terra vs Claude Sonnet 5.5: speed and value vs raw capability — teortaxesTex · 2026-10-27
- Harmonic Teases: AI Taught to Prove Math, 'Something Harder' Coming Soon — satnam6502 · 2026-10-27
- OpenAI quietly swaps Plus/Pro default to cheaper GPT-6.1 Terra and cuts Codex allowance — kimmonismus · 2026-10-27
- 'Never been this uninterested after an OpenAI model release' — theteknosaur · 2026-10-27
- Dev questions reports of Chinese models writing insecure code, citing thin methods and conflicts — dbreunig · 2026-10-27
- Aidan Gomez: LLM probing outside servers was out-of-bounds, not proof of intent — AccBalanced · 2026-10-27