Introducing Kimi K3.1 Pro

Moonshot released Kimi K3.1 Pro, a soon-to-be open-weight model that Artificial Analysis scored at 55, ahead of Claude Fable 5.1, GPT-6 Astra and Gemini 4 Argon (all 53) and behind only Claude Opus 5.5 (58). Kimi K3.1 Pro is priced at $2.00 per million input tokens and $10.00 per million output tokens, the same as GPT-6.1 Sol and half the price of Claude Opus 5.5, with a "Highspeed" version running 2-3x faster at twice the price except for input token cache hits. Simon Willison tested Kimi K3.1 Pro through the Moonshot API using the `llm openai endpoint` command added to LLM 0.32, generating pelican-riding-a-bicycle SVGs at the low, medium and max reasoning levels and comparing them against fresh runs on Kimi K3.

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 https://platform.kimi.ai/docs/pricing/chat 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 https://artificialanalysis.ai/models/kimi-k3-1-pro - 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 https://platform.kimi.ai/docs/get-your-api-key using the llm openai endpoint https://llm.datasette.io/en/stable/other-models.html openai-endpoint command I added to LLM 0.32 https://llm.datasette.io/en/stable/changelog.html v0-32 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 https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2F9b7181492209387da1d4f53002f26663 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 https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Feba9a4283c9e94cbbb5325902a3921a8 on those three reasoning levels. Via Hacker News https://news.ycombinator.com/item?id=50212065 Tags: ai https://simonwillison.net/tags/ai , generative-ai https://simonwillison.net/tags/generative-ai , llms https://simonwillison.net/tags/llms , llm https://simonwillison.net/tags/llm , llm-pricing https://simonwillison.net/tags/llm-pricing , pelican-riding-a-bicycle https://simonwillison.net/tags/pelican-riding-a-bicycle , llm-release https://simonwillison.net/tags/llm-release , ai-in-china https://simonwillison.net/tags/ai-in-china , moonshot https://simonwillison.net/tags/moonshot , kimi https://simonwillison.net/tags/kimi