> ## Documentation Index > Fetch the complete documentation index at: https://www.rumus.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Overview > Use Rumus's built-in models, bring your own API keys, or run local models — sometimes all at once. Rumus is provider-agnostic. You can use the **built-in models** that come with your subscription, **bring your own keys** for any of the major providers, run **local models** through Ollama, or point at **any OpenAI-compatible endpoint**. All configured models appear in the same model picker. ## Pick the right path Easiest. Sign in, pick a Pro plan, done. Pricing, usage, and billing all live in this guide. Pay your provider directly. Useful if you have credits, need a model Rumus doesn't bundle, or your org requires it. Keep everything on your machine via Ollama. No network, no per-token cost. For OpenRouter, vLLM, LiteLLM, LocalAI, an internal gateway — anything that speaks the OpenAI API. ## Bring your own key Rumus has first-class support for these providers. Each one has its own setup guide: } href="/models/anthropic"> Claude Opus, Sonnet, and Haiku. } href="/models/openai"> GPT-5, GPT-4.1, o-series reasoning models. } href="/models/google"> Gemini Pro and Flash. } href="/models/zai"> GLM family, including GLM-4.7 and the Coding variant. } href="/models/deepseek"> DeepSeek V3.2 and the V3.2 Reasoner. } href="/models/kimi"> Kimi K2.5, K2 Thinking, and Moonshot V1. } href="/models/ollama"> Local models — Llama, Mistral, Qwen, and anything else you've pulled. OpenRouter, vLLM, LiteLLM, LocalAI, internal gateways. ## Where models are configured All model setup happens in **Settings → AI → Models**. The page is split into two sections: * **Built-in Models** — read-only list of what your subscription includes. Greyed out if you're not signed in or not on a paid plan. * **Custom Models** — anything you've added with your own key. Click **Add Model** to create one. Custom models you add appear in the chat model picker right next to built-in ones, with a clear label so you know which is which. ## Capabilities you flag per model When adding a custom model, you tell Rumus what the model can do. The agent uses these flags to decide whether to send images, request tool calls, or use prompt caching: | Capability | Meaning | | ---------------------- | -------------------------------------------------------------------------------------------- | | **Tool Calling** | Model supports function/tool calls — required for agentic mode | | **Vision** | Model accepts images as input | | **Prompt Cache** | Model supports prompt caching (reduces cost on repeated prompts) | | **Privacy Protection** | Provider commits to not storing or training on your data — shown as a green shield in the UI | If you're unsure, leave them off; you can edit a model anytime. ## Privacy * **Custom models** — requests go directly from your machine to the provider you configured. Rumus never sees your prompts, completions, or API keys. Keys are stored encrypted in your local [vault](/docs/account/vault). * **Built-in models** — requests are routed through Rumus's API to the underlying provider. We log token counts for billing but not the message contents. See [Vault & encryption](/docs/account/vault) for how local secrets are stored. ## Mixing providers You can register multiple providers at once and switch between them per-thread. Common patterns: * **Built-in for the heavy lifting, Ollama for offline drafting.** * **Anthropic Sonnet for fast iteration, Opus for tricky bugs.** * **OpenAI for vision, OpenRouter for the long tail.** The model picker remembers the last model used per thread, so you can keep parallel conversations on different models without thinking about it. ## Next steps Everything about the included plan: model list, pricing, usage, top-ups. What the agent can actually do once a model is connected.