After DeepSeek R1, there's new model from China that outperforms Claude Sonnet 3.5 & GPT-4o. Kimi is a multimodal model with advanced Chain-of-thoughts reasoning and real-time web search.

☆ Yσɠƚԋσʂ ☆@lemmygrad.ml · 6 months ago

After DeepSeek R1, there's new model from China that outperforms Claude Sonnet 3.5 & GPT-4o. Kimi is a multimodal model with advanced Chain-of-thoughts reasoning and real-time web search.

Che's Motorcycle@lemmygrad.ml · 5 months ago

Yeah, if you create an account with Moonshot, you can then create an API key in their console. In the Cursor settings -> Models, you add a model called moonshot-v1-128k (I think), along with their endpoint and the API key, and you should be in business!

☆ Yσɠƚԋσʂ ☆@lemmygrad.ml · 5 months ago

Ah thanks for the heads up, will have to try this out.

Che's Motorcycle@lemmygrad.ml · 5 months ago

You bet!

After DeepSeek R1, there's new model from China that outperforms Claude Sonnet 3.5 & GPT-4o. Kimi is a multimodal model with advanced Chain-of-thoughts reasoning and real-time web search.

After DeepSeek R1, there's new model from China that outperforms Claude Sonnet 3.5 & GPT-4o. Kimi is a multimodal model with advanced Chain-of-thoughts reasoning and real-time web search.

GitHub - MoonshotAI/Kimi-k1.5