kimi k2.5 | Warp | Page 1

Hi @lament nebula. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

I’m sorry, but the knowledge sources don’t mention Kimi or a “k2.5” model at all, nor any plans for a US‑based Kimi instance.

What is mentioned:

Warp currently uses several cloud AI providers (Anthropic, OpenAI, Google, Fireworks, etc.), but Kimi is not listed among them. [Subprocessors]
There are open feature requests and roadmap notes for:
- Adding/refreshing specific models like GLM 4.7 and Gemini 3 Flash. [GLM 4.7; Gemini 3 Flash]
- Supporting custom AI model configuration and OpenAI‑compatible endpoints in general. [Custom AI config]
- “Bring your own LLM” and local / custom providers (Ollama, LM Studio, etc.), which is on the roadmap but with no ETA. [Local LLMs; Universal BYOLLM]

None of these explicitly mention Kimi or a plan to host a US‑based Kimi k2.5 instance like GLM.

So based on the available information, I can’t confirm that Warp is planning Kimi k2.5 support or a US instance. The closest path would be if/when Warp ships generic custom/OpenAI‑compatible endpoints or broader “bring your own LLM” support, but there’s no specific commitment or timeline in the sources.