> ## Documentation Index > Fetch the complete documentation index at: https://docs.get-hive.ai/llms.txt > Use this file to discover all available pages before exploring further. # AI and models > Which AI providers power Hive, how your data reaches them, how admins restrict models, bring-your-own-key, and how Hive keeps AI output under control. Hive uses large language models to read, reason, write and plan. This page explains which providers are involved, what data they receive, and the controls you have. ## Where AI is used | Feature | What the AI does | | - | - | | **Ask Hive** | Answers questions from your tools, files, the Business Brain and the web, with citations. | | **Signals** | Explains why a detection matters and prepares a proposed next step. | | **Workflows and agents** | Runs the agent, condition, search, image and document steps you configure. | | **Business Brain** | Extracts facts and relationships from your connected data. | | **Monitoring** | Proposes read-only metrics to watch for each connected tool. | In every case the model **proposes**. Whether anything happens in your tools is decided by Hive's deterministic policy engine and, where required, a person. See [Security overview](/security/overview). ## Model providers Hive works with models from several providers: * **OpenAI** * **Anthropic** * **Google** * **xAI** * **Microsoft** Requests reach these providers either directly or through a model gateway provider that routes requests to the model you picked. Embeddings (used to search your knowledge) and image generation use OpenAI. Web search in Ask and in workflows uses **Tavily**, a search provider. Which models appear in your model picker depends on what is configured for your workspace; Hive does not guarantee a fixed list. Each answer records the model that actually produced it. ## What providers receive To answer a request, the model needs context. Hive sends only what that request needs: * your question or the step's instructions; * the relevant excerpts retrieved from your tools, files and Business Brain; * earlier turns of the conversation when **chat memory** is allowed. Hive does **not** send connector credentials, API keys or secrets to any model. Untrusted content — emails, documents, web pages — is clearly marked as data, never instructions. Hive does not send prompts or completions to third-party tracing or observability services. ## Training and your data * **Hive** does not use your workspace's chat and workflow data to improve its product unless an Owner or Admin turns on **Help improve Hive** in **Settings → Workspace → Data sharing**. With it on, the product states: "No personal data will be used." See [Data protection](/security/data-protection#the-data-sharing-setting). * **Model providers** process requests under their own terms for API and enterprise use. If your organisation has specific requirements about a provider, use the model restrictions or bring your own key, below, and [contact us](/help/support) with questions. ## Control which models are used Owners and Admins can restrict the workspace to an allow-list of models in **Settings → Workspace → Models** (up to 50 models). An empty allow-list means no restriction. * Members see only models that are available to them. * Admins also see unavailable models, with the reason — for example, the provider is not configured. * The picker shows **Workspace default**, or **Hive Auto** when automatic routing is the default. * An explicit model choice also governs the planning and retrieval steps behind that answer. See [Models](/ask/models) for the member view. ## Bring your own key If your organisation has its own agreement with **OpenAI** or **Anthropic**, you can fund seats with your organisation's key rather than Hive credits. Requests on those seats are billed by your provider under your agreement. One organisation-wide key is used and only its last four characters are ever shown. See [Billing and plans](/admin/billing-and-plans#bring-your-own-key-byok). ## When credits run out If a member's AI credits run out, chat falls back to an included efficient model rather than failing. Agents can be configured to block usage or switch model when a limit is reached. Workflow and agent runs stop when the workspace's run allowance is used up. ## Keeping AI output honest * **Citations are built by Hive, not the model.** The model points at evidence; Hive fills in the labels and links from the actual sources, and only allows safe https links. * **Live-read failures are disclosed.** If Hive could not check a live source, the answer says so and notes that it relied on stored data that may be out of date. * **Confidence is labelled.** A signal shows whether its confidence is Hive's own estimate or measured. * **Low-trust sources stay low-trust.** Knowledge derived from an untrusted source is never promoted to trusted by the model. ## Related Choosing a model in Ask. Retention, sharing and deletion. Policy engine, approvals and isolation. The providers Hive runs on.