{"id":"kimi-k3-1-pro","slug":"kimi-k3-1-pro","name":"Kimi K3.1 Pro","orgId":"moonshot","family":"kimi-k3-1-pro","releaseDate":"2026-10-23","availability":"ga","openWeights":false,"license":"Proprietary","paramsTotal":null,"paramsSource":null,"contextWindow":1048576,"knowledgeCutoff":null,"modelCardUrl":"https://x.com/Kimi_Moonshot/status/2113680701770068067","hfRepo":null,"modalities":["text","image","video"],"aliases":["Kimi K3.1 Pro","kimi-k3.1-pro","kimi-k3-1-pro","moonshotai/kimi-k3.1-pro","MoonshotAI: Kimi K3.1 Pro","Kimi K3.1 Pro (Max)","Kimi K3 1 Pro","kimi k3.1 pro","moonshotai/Kimi-K3.1-Pro","Kimi-K3.1-Pro"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-23","announced":"2026-10-23","blurb":"Moonshot AI's first K3.1 model, a post-trained version of Kimi K3: a 2.8T-total / 104B-active mixture-of-experts model with a 1M-token context window that takes text, image and video input. Live on Kimi.ai, Kimi Work, Kimi Code and the Kimi API, alongside a Highspeed variant; Moonshot says the full weights will be released by Nov 4, 2026.","api":"live","apiModelId":"kimi-k3.1-pro","openWeights":"announced","params":{"text":"2.8T total / 104B active (MoE)","source":"Moonshot AI's launch post (same architecture as the Kimi K3 model card)"},"facts":[{"label":"Variants","value":"Kimi K3.1 Pro (kimi-k3.1-pro) and Kimi K3.1 Pro Highspeed (kimi-k3.1-pro-highspeed), described by Moonshot as the same capabilities at about 2-3x the speed"},{"label":"Base model","value":"Kimi K3, post-trained further (Moonshot: \"a post-trained version of Kimi K3\")"},{"label":"Context window","value":"1,048,576 tokens"},{"label":"Input","value":"Text, image and video (Moonshot API docs)"},{"label":"API price","value":"K3.1 Pro: $2.00 input / $10.00 output per 1M tokens, cached input $0.20. Highspeed: $4.00 / $20.00, cached input $0.20. Flat pricing, no context tiers"},{"label":"Availability","value":"Kimi.ai, Kimi Work, Kimi Code and the Kimi API, from Oct 23, 2026. API access unlocks after an account top-up (minimum $1)"},{"label":"Weights","value":"Not yet published; Moonshot says the full model weights will be released by Nov 4, 2026"},{"label":"Open-weight release","value":"Moonshot says cyber-related data was removed from mid-training and RL for the open-weight release"}],"claims":["Lab claim: 65.7% on Terminal-Bench 4.0; Moonshot lists GPT-6 Astra at 58.2% and Claude Opus 5.5 at 66.4% on the same chart.","Lab claim: 61.2% on Moonshot's internal Kimi Code Bench 3.0 (long-horizon), up from 55.95% for Kimi K3.","Lab claim: 92.7% on BenchCAD with tools, and 64.4 on OfficeQA Pro v2.","Lab claim: on Moonshot's internal Kimi Hallu Bench Hard, the hallucination rate falls from 23.4% (Kimi K3) to 8.3%.","Lab claim: results were run at maximum reasoning effort, temperature 1.0, top-p 0.95."],"sources":[{"kind":"lab","title":"Kimi (Moonshot AI) announcement on X","url":"https://x.com/Kimi_Moonshot/status/2113680701770068067","date":"2026-10-23"},{"kind":"lab","title":"Kimi K3.1 Pro tech blog","url":"https://www.kimi.ai/blog/kimi-k3-1-pro"},{"kind":"lab","title":"Kimi K3.1 Pro quickstart (Kimi API docs)","url":"https://platform.kimi.ai/docs/guide/kimi-k3-1-pro-quickstart"},{"kind":"lab","title":"Kimi API pricing","url":"https://platform.kimi.ai/docs/pricing/chat"}],"peer":{"slug":"kimi-k3","label":"Kimi K3, the model it is post-trained from"},"pitch":"its most capable 3T-class open-weight model, with a 1M-token context window","firstBenchmark":{"date":"2026-10-24","benchmarkId":"lmarena-webdev"}},"contextSource":"openrouter","listedSince":"2026-10-23","eligibleSince":"2026-10-24","organization":{"id":"moonshot","name":"Moonshot AI","slug":"moonshot","country":null,"url":null,"color":"#8C8C8C","mark":"K"},"price":{"modelId":"kimi-k3-1-pro","provider":"moonshotai","inputPerM":null,"outputPerM":null,"blendedPerM":4.000000000000001,"tokensPerS":null,"observedAt":"2026-11-03","sourceId":"openrouter"},"answer":{"word":"#8","scope":"Best current rank: #8 in Coding › Web dev, as of Nov 3, 2026.","lead":"As of Nov 3, 2026, Kimi K3.1 Pro is ranked #8 in Coding › Web dev (since Nov 3, 2026; sources LMArena WebDev; methodology v1.0). Ranked #8 in Coding › Web dev.","confidence":"medium"},"status":"BENCHMARKED","verdicts":[{"id":"v_overall_general-llm_kimi-k3-1-pro_2026-11-03_open_RANKED","model":"kimi-k3-1-pro","model_name":"Kimi K3.1 Pro","category":"general-llm","category_name":"General LLM","slice":"overall","state":"RANKED","rank":51,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":29.575596816976145,"confidence":"medium","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #51 in General LLM.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#51 in General LLM"},{"id":"v_pareto_general-llm_kimi-k3-1-pro_2026-11-03_open_RANKED","model":"kimi-k3-1-pro","model_name":"Kimi K3.1 Pro","category":"general-llm","category_name":"General LLM","slice":"pareto","state":"RANKED","rank":49,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":28.480204342273296,"confidence":"medium","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #49 in General LLM on best per dollar.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#49 in General LLM (best per dollar)"},{"id":"v_overall_science_kimi-k3-1-pro_2026-11-03_open_RANKED","model":"kimi-k3-1-pro","model_name":"Kimi K3.1 Pro","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":15,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #15 in Science. That board does not award a crown.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#15 in Science"},{"id":"v_overall_coding-web-dev_kimi-k3-1-pro_2026-11-03_open_RANKED","model":"kimi-k3-1-pro","model_name":"Kimi K3.1 Pro","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"overall","state":"RANKED","rank":8,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":5.46875,"confidence":"medium","valid_from":"2026-11-03","valid_to":null,"configuration":null,"rationale":"Ranked #8 in Coding › Web dev.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#8 in Coding › Web dev"},{"id":"v_pareto_coding-web-dev_kimi-k3-1-pro_2026-11-03_open_RANKED","model":"kimi-k3-1-pro","model_name":"Kimi K3.1 Pro","category":"coding-web-dev","category_name":"Coding › Web dev","slice":"pareto","state":"RANKED","rank":8,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":5.46875,"confidence":"medium","valid_from":"2026-11-03","valid_to":null,"configuration":null,"rationale":"Ranked #8 in Coding › Web dev on best per dollar.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#8 in Coding › Web dev (best per dollar)"},{"id":"v_overall_legal_kimi-k3-1-pro_2026-11-03_open_RANKED","model":"kimi-k3-1-pro","model_name":"Kimi K3.1 Pro","category":"legal","category_name":"Legal","slice":"overall","state":"RANKED","rank":22,"present_evidence":[],"missing_evidence":[],"coverage":null,"segments":[],"confirm":[],"margin":null,"confidence":"low","valid_from":"2026-11-03","valid_to":null,"configuration":"max","rationale":"Ranked #22 in Legal. That board does not award a crown.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#22 in Legal"}]}