2026年10月23日 - 链接博客
介绍 Kimi K3.1 Pro (来源) Kimi K3.1 Pro 今日上线 Kimi API——它尚未开源权重,但 Moonshot 承诺“完整模型权重将于 2026 年 11 月 4 日发布”。
他们还提供了一个“高速”版本,速度提升 2-3 倍,价格翻倍(输入 token 缓存命中除外,其定价相同)。
美元定价为每百万输入 token 2.00 美元,每百万输出 token 10 美元——与 GPT-6.1 Sol 相同,是 Claude Opus 5.5 价格的一半。
Moonshot 自身的基准测试显示,Kimi 大致与 Opus 5.5 和 GPT-6 Astra 持平——在部分基准测试中超越它们,在其他基准测试中接近它们。
Artificial Analysis 给 Kimi 评分为 55——高于 Claude Fable 5.1、GPT-6 Astra 和 Gemini 4 Argon(均为 53),仅低于 Claude Opus 5.5(58)。
这是首次有(即将开源权重的)模型在与前沿模型的对比中获得如此高的分数。
我通过 Moonshot API 尝试了该模型,使用了我在今年 8 月添加到 LLM 0.32 中的 llm openai endpoint 命令:
llm openai endpoint \
https://api.moonshot.ai/v1 \
--key kimi \
-m kimi-k3.1-pro \
"Generate an SVG of a pelican riding a bicycle" \
--responses \
-o reasoning_effort low \
> kimi-k3.1-pro-pelican-low.stdout.txt \
2> kimi-k3.1-pro-pelican-low.stderr.txt
llm openai endpoint 可以对任何兼容 OpenAI 的端点运行提示词,但它不记录结果,因此需要额外的选项来保存 stdout 和 stderr(推理轨迹)。
这里是我对 Kimi K3.1 Pro 在其支持的三个推理级别(低、中、高)上生成的鹈鹕图片。这是最高级别的结果:

作为对比,我在相同的三个推理级别下对 Kimi K3 重新运行了鹈鹕生成任务。
查看原文
23rd October 2026 - Link Blog
Introducing Kimi K3.1 Pro (via) Kimi K3.1 Pro landed on the Kimi API today - it's not yet open weights, but Moonshot promise "Full model weights will be released by Nov 4, 2026".
They're also offering a "Highspeed" version that's 2-3x faster, at twice the price (except for input token cache hits, which are priced the same).
The US dollar pricing is $2.00/million tokens for input and $10/million for output - the same as GPT-6.1 Sol and half the price of Claude Opus 5.5.
Moonshot's own benchmarks show Kimi as approximately level with Opus 5.5 and GPT-6 Astra - beating them on a few benchmarks, coming close on others.
Artificial Analysis scored Kimi at 55 - ahead of Claude Fable 5.1, GPT-6 Astra, and Gemini 4 Argon (all at 53) and behind only Claude Opus 5.5 (58).
This is the first time a (soon-to-be) open weight model has scored this highly against the frontier.
I tried it out via the Moonshot API using the llm openai endpoint command I added to LLM 0.32 back in August:
llm openai endpoint \
https://api.moonshot.ai/v1 \
--key kimi \
-m kimi-k3.1-pro \
"Generate an SVG of a pelican riding a bicycle" \
--responses \
-o reasoning_effort low \
> kimi-k3.1-pro-pelican-low.stdout.txt \
2> kimi-k3.1-pro-pelican-low.stderr.txt
llm openai endpoint can run prompts against any OpenAI-compatible endpoint but doesn't log the results, hence the extra options to save stdout and stderr (the reasoning trace).
Here are the pelicans I got for Kimi K3.1 Pro on the three reasoning levels it supports - low, medium, and max. This is max:

For comparison, I ran fresh pelicans against Kimi K3 on those three reasoning levels.
原文版权归 Simon Willison 及原作者所有,本站转载仅供阅读。如需删除,请联系 support@aisa.one。