> ## Documentation Index > Fetch the complete documentation index at: https://docs.cloosphere.ai/llms.txt > Use this file to discover all available pages before exploring further. # Models > Manage model list, set default model, control display order, import/export presets Admin › Settings › Models Manage the list of models from the LLM providers registered in [Connections](/en/admin/settings/connections). * From this tab, control individual model activation, customization, display order, and default model selection. Model management tab *** ## Model List Shows Workspace models (admin-created/customized) combined with Base models (system models pulled from connected APIs). * You can filter by name/ID with the **Model Search** input at the top of the list. | Item | Description | | ---------------------- | -------------------------------------------------- | | **Model name** | Model name shown to users | | **ID** | Model identifier used in API calls | | **Enabled / Disabled** | Toggle (Switch) for whether the model is available | Each model row also shows **dependency badges** counting the agents, flows, and evaluations that reference it (e.g. `Agents 6`, `Flows 1`, `Evaluations 9`), so you can see at a glance where the model is used (the same dependency information as **Used by** at the bottom of the model editor). ### Hide Model (Shift+Click) Hold **Shift** and click the icon in a model row to toggle hide/show. Hidden models are managed as `meta.hidden` and don't appear in the user's model picker. Hidden and Disabled are separate features. Hidden removes from the model picker; Disabled makes the model itself unavailable. *** ## Default Model and Order Click the settings (gear) icon at the top-right of the model list to open the model settings modal. | Setting | Description | | ----------------- | -------------------------------------------------- | | **Default model** | Model auto-selected when starting a new chat | | **Model order** | Display order in the model picker (drag or arrows) | *** ## Activate / Deactivate Models Use per-model **Enabled / Disabled** toggle (Switch) to expose only needed models to users. Disabled models don't appear in the user's model picker dropdown. Disabling a model that's set as an agent's base model doesn't affect agent execution. *** ## Model Customization Click the **edit (pencil) icon** on a model row to customize that model. | Setting | Description | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **Model name / ID** | User-facing name and the identifier used in API calls | | **Model image** | Change or reset the model avatar image | | **Task Prompt** | The default system prompt — describe the role, behavior, and constraints (uses the default if left empty). Use the **AI** button on the right to refine your draft | | **Response Format Prompt** | Specify the markdown style, structure, tone, and length of responses (default format if empty). An **AI** button is provided | | **Advanced Params** | Temperature, Top P, Top K, Stop tokens, etc. (expand via **Advanced Params > Show**) | | **Guardrails** | Connect the guardrails to apply to this model | | **Capabilities** | Enable web search, image generation, etc. | | **Access** | Expose only to specific groups/users | **Knowledge base, database, tool, and glossary connections and auto-evaluation are agent-only.** They aren't offered in the admin model editor — configure them under [Workspace > Agents](/en/workspace/agents). The only runtime resource applied from the model editor is **guardrails**. Customizing a model creates a **Workspace setting record** for that model. Unlike agents, this doesn't directly modify the base model — it adds an **override configuration**. *** ## Controlling Models Visible to Users | Mechanism | Effect | Where to Configure | | -------------------------------- | ------------------------------------- | ------------------------------- | | **Activate/Deactivate** (toggle) | Disabled → excluded from model picker | Toggle on model row | | **Hide** (Shift+click) | Hidden → excluded from model picker | Shift+icon on model row or menu | | **Default model** | Auto-selected on new chat | Settings modal | | **Display order** | Order in model picker dropdown | Settings modal (drag) | | **Access control** | Only specific groups/users | Edit model > Access control | Use **Hide** to temporarily conceal from the list only; use **Disable** to fully block use. (For the difference between the two, see the "Hide Model" description above.) *** ## Token Limits Limit daily token usage per model to manage AI usage cost. * Set the global default with the **`Token Limit` button at the top-right** of the model list. * Set per-model limits with the **`Token Limit` dropdown on each model row**. ### Global Token Limit (Token Limit button) | Item | Description | | ----------------------------- | -------------------------------------------------------------------------------------------------------------------- | | **Enable usage limits** | Overall ON/OFF for the token limit feature | | **Default daily token limit** | Applied to all models without a separate limit set on their row (`0` = unlimited, empty = follow the global setting) | | **Excess action** | **Warn** (show message only and allow usage) or **Block** (block additional usage) | ### Per-Model Limits Set an individual daily limit for a model with the **`Token Limit` dropdown on its row**. Models without one follow the default daily token limit above. Admin role users are excluded from token limit checks. Limits can be set at 4 levels — global, user, group, organization — and when set in multiple places, the **most permissive (highest)** value applies. Check per-user and per-model usage in the usage tab of [User Management](/en/admin/users#usage-limits). *** ## Ollama Model Management Click the **download icon** at the top of the model list to open the Ollama model management modal. | Feature | Description | | -------------- | -------------------------------------------------------------------- | | **Pull** | Download a model from the Ollama model registry (up to 3 concurrent) | | **Update All** | Update all Ollama models to latest versions | | **Upload** | Upload a GGUF file or download from URL to create a model | | **Delete** | Delete an Ollama model | When multiple Ollama instances are connected, you must first pick the instance to manage. *** ## Model Preset Import / Export Back up and restore model settings as JSON. * This feature is **admin-only**. | Feature | Description | | ------------------ | --------------------------------------------- | | **Import Presets** | Restore model presets from a JSON file | | **Export Presets** | Download current model presets as a JSON file | | **Single Export** | More menu (⋯) on a model row > Export | Import overwrites existing model settings. Always Export to back up first. Only models with null `base_model_id` (Workspace custom settings) are imported. Agents (which reference another model via `base_model_id`) aren't imported in this tab — import them separately under Workspace > Agents. Click **Reset All Models** at the bottom of the settings modal (gear) to delete all Workspace custom settings. Connected base model lists are preserved, but customizations like name/description/prompt are all reset. *** ## Related Pages Configure LLM provider API connections AI assistants combining Knowledge Bases, tools, and guardrails on top of a model Per-model token usage and cost analysis