Model Brief

Kimi K2.5 Cloud

Moonshot AI's native multimodal agentic model for vision-language understanding, coding, reasoning, tool use, and complex agent workflows. Deployed through Terminal.Glass via a cloud-only tag routed to Ollama Cloud -- 1.04T parameters, 256K context, text and image input, and configurable thinking mode without provisioning trillion-parameter local hardware.

Quick Facts

DeveloperMoonshot AI
LicenseDescribed as open-source; Kimi-family licensing has used modified MIT-style terms -- verify current terms at the official model card before commercial use
Size1.04T parameters
Context Window256K tokens
Cloud Variantkimi-k2.5:cloud (high usage tier -- only tag currently on Ollama)
ModalityText and image input; configurable thinking mode; native tool support
Local HardwareNo local weight variant currently listed on Ollama -- cloud is the practical access path
Best ForMultimodal agents, visual reasoning, UI-to-code workflows, long-context research

Why Choose This Model

Kimi K2.5 is a native multimodal agent capable of interpreting images alongside text -- useful for visual document review, UI-to-code workflows, coding against visual specifications, and multi-step agent orchestration with tool calling. Its 256K context and configurable thinking mode support long-context debugging and complex reasoning chains. Because it is currently only available as a cloud tag, Terminal.Glass is a practical way to evaluate a trillion-parameter multimodal model without provisioning matching local hardware.

Terminal.Glass Deployment

Your interface, chat history, user accounts, and RAG index stay on your Terminal.Glass host. When you submit a prompt -- including uploaded images, code excerpts, and any retrieved RAG passages -- to kimi-k2.5:cloud, the request is forwarded to Ollama Cloud, where Kimi K2.5 runs, and the response streams back. Cloud access requires an Ollama account signed in on the Terminal.Glass machine (ollama signin). Kimi K2.5 is rated high usage on Ollama -- budget accordingly for image inputs, long 256K contexts, thinking-mode prompts, and agentic tool loops. No local GPU is required to use the cloud tag.

Recommended Uses

Not appropriate for regulated, confidential, or strict data-residency workloads -- prompts, uploaded images, code snippets, RAG-retrieved passages, and tool context are sent to Ollama Cloud during inference. Avoid sensitive screenshots, client visuals, or proprietary UI designs unless your organization has explicitly approved cloud processing for that data class. Generated code and agent tool actions still require tests, review, permissions, and rollback discipline regardless of model capability. Cloud inference does not pin model versions the way a local checkpoint does, so confidential or citable research data should stay on a fully local deployment.

Hardware Guidance

The kimi-k2.5:cloud tag runs entirely on Ollama Cloud, so the Terminal.Glass host only needs to run Open WebUI, the Ollama client, and your document index -- a small VM or mini-PC is sufficient. Ollama currently lists no local weight variant for Kimi K2.5, so self-hosting a 1.04T-parameter model is not a practical option for most teams today. Confirm current tag availability at the official Ollama listing.

Honest Guidance

Learn More

Full technical reference, licensing detail, and local deployment options for this model family are documented on NoCloudGPT. Confirm current tags and availability at ollama.com/library/kimi-k2.5.

Deploy with Terminal.Glass → View Pricing Contact