Kimi K2 Thinking, a SOTA open-source trillion-parameter reasoning model

Re:Kimi K2 Thinking, a SOTA open-source trillion-parameter r... by mrbonner on Thursday November 06, 2025 @07:06PM (#45842152)

I suspect that the OpenRouter result originates from a quantized hosting provider. The difference compared to the direct API call from Moonshot is striking, almost like night and day. It creates a peculiar user and developer experience since OpenRouter enforces quantization restrictions only at the API level, rather than at the account settings level.

[ Parent | on HN ]

Re:Kimi K2 Thinking, a SOTA open-source trillion-parameter r... by simonw on Thursday November 06, 2025 @08:29PM (#45842646)

OpenRouter are proxying directly through to Moonshot - they're currently the only provider listed on https://openrouter.ai/moonshotai/kimi-k2-thinking/providers

[ Parent | on HN ]

Re:Kimi K2 Thinking, a SOTA open-source trillion-parameter r... by irthomasthomas on Friday November 07, 2025 @03:43AM (#45844630)

That does include the Turbo endpoint, moonshotai/turbo. Add this to your prompt to only use the full-fat model:

-o provider '{ "only": ["moonshotai"] }'

[ Parent | on HN ]