{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/kimi-k3/","md":"https://postcutoff.com/m/kimi-k3/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"kimi-k3","name":"Kimi K3","org":"Moonshot AI","family":"Kimi K3","released":"2026-07-16","status":"current","type":"reasoning-llm","modality_in":["text","image","video"],"modality_out":["text"],"open_weights":true,"model_license":"kimi-k3 (custom)","context_window":1048576,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":3,"output":15,"cache_read":0.3,"cache_write_5m":3,"cache_write_1h":6,"unit":"per 1M tokens (USD)","source":"https://platform.kimi.ai/docs/pricing/chat"},"price_line":"$3 in, $15 out per 1M tokens","access":[{"provider":"Kimi API (Moonshot)","model_id":"kimi-k3","endpoint":"https://api.moonshot.ai/v1","docs":"https://platform.kimi.ai/docs/guide/kimi-k3-quickstart"},{"provider":"Alibaba Cloud Model Studio","model_id":"kimi-k3","docs":"https://www.alibabacloud.com/help/en/model-studio/models"},{"provider":"OpenRouter","model_id":"moonshotai/kimi-k3","url":"https://openrouter.ai/moonshotai/kimi-k3"},{"provider":"Hugging Face","url":"https://huggingface.co/moonshotai/Kimi-K3"},{"provider":"Web app","url":"https://www.kimi.com"}],"capabilities":[{"name":"First open 3T-class model","detail":"2.8T-parameter MoE (16 of 896 experts active) - Moonshot's claim: the first open model at this scale; weights released after launch (promised by 2026-07-27).","first":true,"discovered":"launch","source":"https://www.kimi.com/blog/kimi-k3"},{"name":"Kimi Delta Attention + Attention Residuals","detail":"Hybrid linear attention (KDA) and AttnRes; ~2.5x the scaling efficiency of K2 per Moonshot.","first":false,"discovered":"launch","source":"https://platform.kimi.ai/docs/guide/kimi-k3-quickstart"},{"name":"Native vision with 1M context","detail":"Native visual understanding (image and video) and a 1,048,576-token window; strong at coding tasks that use screenshots/visual feedback (games, frontend, CAD).","first":false,"discovered":"launch","source":"https://platform.kimi.ai/docs/guide/kimi-k3-quickstart"},{"name":"Always-on thinking with effort control","detail":"Thinking cannot be disabled; reasoning_effort low/high/max (default max).","first":false,"discovered":"launch","source":"https://platform.kimi.ai/docs/guide/kimi-k3-quickstart"}],"entry":null,"notes":"Moonshot flagship. API unlocked after a minimum $1 top-up. Chat Completions, Responses and Anthropic-compatible Messages supported. Max output and knowledge cutoff not verified. Docs moved to platform.kimi.ai (platform.moonshot.ai still serves).","verified":"2026-09-29","body_md":"Moonshot's frontier open model for long-horizon coding, knowledge work and deep reasoning; 1M context, vision.\n\n```bash\ncurl https://api.moonshot.ai/v1/chat/completions \\\n -H \"Authorization: Bearer $MOONSHOT_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"kimi-k3\",\"reasoning_effort\":\"high\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'\n```\n\nSources: https://platform.kimi.ai/docs/guide/kimi-k3-quickstart · https://platform.kimi.ai/docs/pricing/chat · https://platform.kimi.ai/docs/models · https://www.kimi.com/blog/kimi-k3","page_url":"https://postcutoff.com/m/kimi-k3/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":1760,"you_url":"https://postcutoff.com/you/kimi-k3/","briefings":null}