{"schema":"postcutoff/model@1","as_of":"2026-10-25T23:49:00+01:00","url":"https://postcutoff.com/m/kimi-k3-1-pro/","md":"https://postcutoff.com/m/kimi-k3-1-pro/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-k3-1-pro","name":"Kimi K3.1 Pro","org":"Moonshot AI","family":"Kimi K3","released":"2026-10-23","status":"current","type":"reasoning-llm","modality_in":["text","image"],"modality_out":["text"],"open_weights":false,"model_license":"proprietary until weights are released (promised by 2026-11-04; licence not yet named)","context_window":1048576,"max_output":null,"knowledge_cutoff":null,"pricing":{"input":2,"output":10,"cache_read":0.2,"unit":"per 1M tokens (USD)","source":"https://openrouter.ai/moonshotai/kimi-k3.1-pro"},"price_line":"$2 in, $10 out per 1M tokens","access":[{"provider":"Kimi API (Moonshot)","model_id":"kimi-k3.1-pro","endpoint":"https://api.moonshot.ai/v1","docs":"https://platform.kimi.ai/docs/models"},{"provider":"Kimi API (Moonshot), fast variant","model_id":"kimi-k3.1-pro-highspeed","endpoint":"https://api.moonshot.ai/v1"},{"provider":"OpenRouter","model_id":"moonshotai/kimi-k3.1-pro","url":"https://openrouter.ai/moonshotai/kimi-k3.1-pro"},{"provider":"Web app","url":"https://www.kimi.com"}],"capabilities":[{"name":"Near-frontier score for a soon-open model","detail":"Artificial Analysis Intelligence Index 55 at launch, 4th overall behind Claude Opus 5.5 (58), Sonnet 5.5 (56) and Muse Wonder Full (56); highest Terminal-Bench 4.0 score AA had measured (67%); GDPval-AA 1,846 Elo.","first":true,"discovered":"launch","source":"https://x.com/ArtificialAnlys/status/2113688083145314416"},{"name":"Cyber-capability data removal","detail":"Moonshot removed cyber-related data from both mid-training and RL so the open weights would not extend the frontier of offensive cyber capability; the unfiltered checkpoint scored 90.5 vs 81.0 on xdev-bench-hard.","first":true,"discovered":"launch","source":"https://www.kimi.ai/blog/kimi-k3-1-pro"},{"name":"Game-engine and CAD work","detail":"Marketed for full-project coding in Unreal, Unity and Godot and for parametric 3D modelling in Blender and CAD (BenchCAD with tools 92.7% Voxel IoU).","first":false,"discovered":"launch","source":"https://www.kimi.ai/blog/kimi-k3-1-pro"}],"entry":"2026-10-23-kimi-k3-1-pro","notes":"2.8T total / 104B active MoE, 1M context. Highspeed variant is 2–3x faster at about twice the price, with the same cached-input price (Simon Willison). Defaults: reasoning effort max, temperature 1.0, top_p 0.95. Enterprise admins must enable it (off by default). Zero Data Retention available on the API. Max output and knowledge cutoff not verified; Kimi's own pricing page did not render prices for our fetcher, so prices are OpenRouter's (matching Willison's $2/$10).","verified":"2026-10-24","body_md":"Moonshot's follow-up to Kimi K3. API live at launch on Oct 23, 2026; weights promised by Nov 4, 2026.\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-k3.1-pro\",\"reasoning_effort\":\"max\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello\"}]}'\n```\n\nSources: https://www.kimi.ai/blog/kimi-k3-1-pro · https://openrouter.ai/moonshotai/kimi-k3.1-pro · https://simonwillison.net/2026/Oct/23/kimi-k31-pro/","page_url":"https://postcutoff.com/m/kimi-k3-1-pro/","events_after":null,"major_after":null,"historic_after":null,"missing_at_launch":null,"events_since_release":5,"you_url":"https://postcutoff.com/you/kimi-k3-1-pro/","briefings":null}