{"version":1,"type":"story","url":"https://digestai.news/story/moonshot-ai-s-kimi-k3-opens-on-amazon-bedrock-with-2-8-trillion-parame","json":"https://digestai.news/story/moonshot-ai-s-kimi-k3-opens-on-amazon-bedrock-with-2-8-trillion-parame.json","markdown":"https://digestai.news/story/moonshot-ai-s-kimi-k3-opens-on-amazon-bedrock-with-2-8-trillion-parame.md","slug":"moonshot-ai-s-kimi-k3-opens-on-amazon-bedrock-with-2-8-trillion-parame","headline":"Moonshot AI's Kimi K3 opens on Amazon Bedrock with 2.8 trillion parameters","summary":"Moonshot AI announced that its Kimi K3 model is now available on Amazon Bedrock. The model is described as the first open‑weight model to reach 2.8 trillion parameters and adds native vision support with a 1-million-token context window. Moonshot AI says Kimi K3 offers an approximate 2.5x improvement in scaling efficiency over its predecessor Kimi K2, making it suitable for long‑running coding and knowledge workflows that need sustained context across large codebases, documents, and images.\n\nAmazon Bedrock provides explicit prompt caching for Kimi K3, allowing developers to mark reusable prompt prefixes after at least 1,024 tokens. Cached tokens are billed at a higher rate but remain in cache for at least 30 minutes, and subsequent matching requests receive discounted input‑token pricing and no input‑tokens‑per‑minute quota impact. Global cross‑Region inference with the model costs approximately 10% less than a geographic profile, while a US‑only profile satisfies data‑residency requirements. The model can be accessed via the Bedrock console, the OpenAI‑compatible APIs, or through open‑source agents such as OpenCode and Hermes that support Bedrock providers.","keyPoints":["Kimi K3 is the first open‑weight model with 2.8 trillion parameters and a 1-million-token context window","Explicit prompt caching reduces latency and input‑token costs, with cached content kept for at least 30 minutes","Global cross‑Region inference costs approximately 10% less than a geographic profile"],"whyItMatters":"The model brings a trillion‑parameter open‑weight LLM to a widely used cloud platform, giving developers high‑capacity AI with built‑in data security and cost‑saving caching features.","category":{"slug":"models","name":"Generative AI & Models","url":"https://digestai.news/category/models"},"entities":{"companies":["Moonshot AI","Amazon","AWS","OpenAI","Google","NVIDIA"],"models":["Kimi K3","Kimi K2"],"people":[]},"firstPublishedAt":"2026-09-18T16:52:01Z","updatedAt":"2026-09-18T17:07:01Z","sourceCount":2,"hasPrimarySource":true,"sources":[{"outlet":"AWS Machine Learning Blog","title":"Introducing Kimi K3 on Amazon Bedrock","url":"https://aws.amazon.com/blogs/machine-learning/introducing-kimi-k3-on-amazon-bedrock","publishedAt":"2026-09-18T16:52:01Z","type":"primary","primary":true,"lead":true},{"outlet":"Unite.AI","title":"Moonshot AI’s Kimi K3 Arrives on Amazon Bedrock With 1M-Token Context","url":"https://unite.ai/moonshot-ais-kimi-k3-arrives-on-amazon-bedrock-with-1m-token-context","publishedAt":"2026-09-18T17:07:01Z","type":"press","primary":false,"lead":false}],"sourceNotes":null,"discussions":[],"thread":{"title":"Moonshot AI's Kimi Takes Global Stage","url":"https://digestai.news/thread/moonshot-says-kimi-is-used-by-chinese-investment-banks-and-vcs-reportedly-files","storyCount":2},"cite":{"text":"Digest AI, \"Moonshot AI's Kimi K3 opens on Amazon Bedrock with 2.8 trillion parameters\", 18 September 2026, https://digestai.news/story/moonshot-ai-s-kimi-k3-opens-on-amazon-bedrock-with-2-8-trillion-parame","publisher":"Digest AI","title":"Moonshot AI's Kimi K3 opens on Amazon Bedrock with 2.8 trillion parameters","datePublished":"2026-09-18T16:52:01Z","url":"https://digestai.news/story/moonshot-ai-s-kimi-k3-opens-on-amazon-bedrock-with-2-8-trillion-parame"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}