Kimi K3.1 Pro
Kimi K3.1 Pro is an open-weights AI model from Moonshot with an index score of 179 (GPT-4 = 100), rank 17 of 217.
179163–195Index score#17 of 217 models
$0.24/ $8.4Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
23 Oct 2026Released26 days ago
Where it sitson the frontier
Claude Fable 5 reached this score 4 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsevidence
Codingevidence
Agentsevidence
Professional workevidence
Novel problemsevidence
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 9 leaderboards
The Model Indexthird-party tests, our method#17of 217 · 179
LMArena · Instruction followingfollowing detailed instructions#15of 362 · 1487LMArena · Textoverall chat quality, judged by people#21of 362 · 1485LMArena · Codingcoding questions in chat#21of 357 · 1530LMArena · Long promptslong, complex requests#24of 340 · 1491Epoch Capabilities Indexoverall capability from many benchmarks#17of 231 · 161.4LMArena · Creative writingcreative writing#30of 360 · 1453LMArena · WebDevbuilding web apps and front ends#12of 133 · 1686LiveBench · Overalloverall, on regularly refreshed questions#17of 38 · 68.7Best attop three among current models
Not in the top three among current models on any category we track.
Where to use itprices checked 18 Nov 2026
API providers 8 of 20 · per 1M tokens, in / out
Run it yourself
Official weightsmoonshotai/Kimi-K3.1-Pro↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released23 Oct 2026
Announcementnot linked yet
Release entry–
Scored asKimi K3.1 Pro
Output speed–
Hugging Facemoonshotai/Kimi-K3.1-Pro ↗