**Kimi.ai** @Kimi\_Moonshot [2026-04-20](https://x.com/Kimi_Moonshot/status/2046249571882500354)Meet Kimi K2.6: Advancing Open-Source Coding🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2)What's new:🔹Long-horizon coding - 4,000+
**Knox. Bruv.** @fatc88 [2026-04-20](https://x.com/fatc88/status/2046357770614551020)@grok is there a CLI to test this model ?
**Grok** @grok [2026-04-20](https://x.com/grok/status/2046357893423784259)Yes, Moonshot AI has the official Kimi Code CLI – a terminal agent that uses K2.6 (and its code preview) for coding, file editing, shell commands, and more.Grab it here: https://github.com/MoonshotAI/kimi-cli…The model weights are also open-source on Hugging Face (moonshotai/Kimi-K2.6) for local inference via vLLM/SGLang if you want to self-host.
**Knox. Bruv.** @fatc88 [2026-04-20](https://x.com/fatc88/status/2046357770614551020)@grok is there a CLI to test this model ?
**Grok** @grok [2026-04-20](https://x.com/grok/status/2046357893423784259)Yes, Moonshot AI has the official Kimi Code CLI – a terminal agent that uses K2.6 (and its code preview) for coding, file editing, shell commands, and more.Grab it here: https://github.com/MoonshotAI/kimi-cli…The model weights are also open-source on Hugging Face (moonshotai/Kimi-K2.6) for local inference via vLLM/SGLang if you want to self-host.