The AI Models page decides which AI models the organization can use and which model powers each platform feature by default. Organizations that Qlar allows to bring their own AI models also connect their own provider keys and gateways here. For step-by-step guides, see Bring Your Own Key and Connect a Gateway. Open it with the AI Models tile on the organization's menu page.
Access
| |
|---|
| Owner/Admin | Can view and change everything on this page. |
| Other Roles | The AI Models tile is not shown. Opening the page by its address shows "Only organization Owners and Admins can open AI Models." |
Tabs
The page has three tabs. The open tab is kept in the address (?tab=models, ?tab=sources, ?tab=defaults), so a refresh or the browser's Back button returns to the same tab.
| |
|---|
| Models | Every model the organization can use, with its on/off switch. Opens by default. |
| Sources | The organization's Gateways and provider API keys. Shown only for organizations allowed to bring their own AI models or to use gateways (and, while gateways are turned off, for an organization that still has some); elsewhere ?tab=sources opens Models. |
| Defaults | Which model powers each feature. |
| On a phone | The tabs share the screen width evenly. |
Offline Gateway Banner
Above the tabs, one warning per gateway that is offline while its models are switched on: "Office PC is offline, so sonnet-office can't answer right now." It adds "It powers the default for …" when one of those models is a feature default. Bring it back online opens the gateway's Bring it back online panel on Sources.
Models Tab
Models are grouped by where they come from. Each row shows the model's alias, a one-line description, chips for what it accepts and produces (for example Image in, Document in, Audio out, or Text only), and a switch.
| |
|---|
| Filter chips | All, Qlar, API key, and Gateway, each with its model count. API key is shown only where the organization may bring its own keys, Gateway only where it may use gateways. |
| Search models | Narrows the rows by alias or description. |
| Qlar | Built-in models, billed with Qlar credits. The description includes the credit multiplier, for example "3× credits". |
| Your API keys | Models reached with the organization's own provider keys. No Qlar credit is charged for these. Add API key opens the Add / Edit API Key dialog. |
| Your gateways | Models on the organization's gateways. No Qlar credit is charged for these. Connect a gateway opens the Connect a Gateway wizard. Each row shows the tool and model, then where it runs: ● Office PC while online, ○ Office PC, offline 3 h ago while not, or Office PC · not offered by this computer when the computer no longer offers that model. |
| Switch | Turns the model on or off for the organization. A model turned off is hidden from every agent. |
| Default chip | Default followed by the features this model powers, for example "Default · Conversation". |
| Locked Switch | A Qlar model that is the default for a feature cannot be turned off. Change that feature's default first; the tooltip names the features. |
| On a phone | Rows show only the name, description and switch. Tap a row to open a sheet with its capability and default chips; Close dismisses it. |
Sources Tab
The tab has two sections, Gateways and API keys. Each is shown only where the organization may use it; Gateways also stays visible while gateways are turned off for an organization that still has some.
Gateways
| |
|---|
| Connect a gateway | Opens the Connect a Gateway wizard in place of the list. |
| Turned off | "Gateways are turned off for this organization, so their models can't be used. Everything comes back as it was when Qlar turns them on again. You can still remove a gateway." Cards are read-only and offer Remove only. |
| Empty State | No gateways yet. Connect a computer to use your own Claude or ChatGPT account instead of Qlar credits. |
| Card | The gateway's name, a status chip, ● Online or ○ Offline · last seen …, then the computer's name, system, gateway version and "n of 2 jobs running", a chip per tool with how it signs in (for example Claude Code · subscription (Max)), and its models. |
| ⋯ menu | Rename, Move to another computer (approved gateways), and Remove…. |
Card status and the button it offers:
| Status chip | Meaning | Button |
|---|
| Connected · ● Online | Approved and running. | Models · n: add or remove its models. |
| Connected · ○ Offline | Approved, but not running or not reachable. | Bring it back online |
| Waiting for the command to run | The setup command hasn't reported in. Its code can't be shown again. | Get a new code |
| Code expired | The command was never run within 15 minutes. | Get a new code |
| Waiting for your approval | The gateway enrolled; its fingerprint waits for approval. | Review fingerprint |
| Moving to a new computer | A move is waiting for its command on the new computer. The current computer keeps working. | Get a new code |
| New computer waiting for approval | The new computer enrolled; the current one keeps working until you approve it. | Review fingerprint |
| Move: code expired | The code for the new computer expired before it was used. | Get a new code |
| Revoked | The gateway can't connect any more. | Remove |
| No longer registered | The gateway service no longer knows this gateway. | Remove |
| Status unavailable | Qlar couldn't reach the gateway service to check it. | Retry |
Bring it back online
Opened from an offline card or the offline banner.
| |
|---|
| Same computer | The commands to start it again: qlar-inference-gateway run in a terminal, or the restart command for a service (Windows schtasks /Run /TN "Qlar Inference Gateway", macOS launchctl kickstart -k gui/$(id -u)/ai.qlar.inference-gateway, Linux sudo systemctl restart qlar-inference-gateway), and the install-service command so it survives the next restart. The card turns green as soon as it reports in. |
| New or reset computer | Get a new code starts a move to another computer. Its models, the agents using them and their settings stay as they are. |
API keys
| |
|---|
| API keys | One card per key: the alias, then provider, model or deployment name, endpoint, masked key, and "turned off" when the model is switched off under Models. |
| Add API key | Opens the Add / Edit API Key dialog. |
| Edit | Opens the same dialog for that key, with Delete available. |
| Empty State | No API keys yet. |
Connect a Gateway Wizard
Opens in place of the Sources list, titled Connect a gateway (Move name to another computer when moving, Models on name when adding models), with "Step n of 4" and a progress bar. × closes it; setup continues from the gateway's card. A refresh keeps the wizard open (?gateway= in the address).
| Step | Fields and buttons |
|---|
| 1 Where | Name (required, at most 100 characters, shown to your team in model lists) and Where will it run?: Windows (Windows 10 or 11, x64), macOS (Apple silicon), Linux (x64 or arm64). Create code creates the gateway and a one-time code that expires after 15 minutes. |
| 2 Run | The command for the chosen system, with links to switch to the other systems. Copy command; on a phone or where sharing is supported, Send to my computer…. The One-time code with its own copy button, and the shorter enroll command for a computer that already has the gateway. A countdown while waiting for the gateway to report in. Get a new code when the code expired or the page was reloaded. Cancel deletes a gateway that was never approved. |
| 3 Confirm | A gateway has enrolled — confirm it is yours: the computer's name, system and gateway version, and the Key fingerprint (SHA-256) as 4 rows of 4 groups. Fingerprint matches — approve, or It doesn't match — cancel. If the key changes while you compare, Show the new fingerprint. |
| 4 Sign in | How each tool is signed in (subscription, API key, not signed in with the command to run, or Waiting for sign-in…), then Choose models to make available: a checkbox and a name for each model. Names use lower-case letters, digits, ., _ or -, no +, and must not clash with another model. A model of a tool that isn't signed in shows "sign in to use it". Keep it running after a restart shows the install-service command for the system. Finish adds the ticked models; Skip for now closes without adding. |
Rename and Remove Gateway Dialogs
| |
|---|
| Rename name | Name (at most 100 characters). Save. Only the name in Qlar changes. |
| Remove name? | Explains that the gateway is disconnected and can't be used again, and lists its models. Then what else changes: the features whose default goes back to the Qlar default (which uses Qlar credits), the agents whose models fall back to the organization default, and the agents whose voice calls stop until another voice is chosen (they don't move to a Qlar voice). Keep it or Remove gateway. A gateway that was never approved is removed without this dialog. |
Add / Edit API Key Dialog
The dialog is titled Add custom model when adding and Edit "alias" when editing: each API key entry is one model reached with that key.
| |
|---|
| Alias | Required. The name the model is known by in the CMS. Must be unique and must not clash with a predefined alias. Cannot be changed after creation. |
| Provider | OpenAI, Azure OpenAI, Azure AI Inference, or DeepSeek. |
| Invocation method | Chat Completion or Response API. DeepSeek supports Chat Completion only. |
| Native model name | The provider's model name, for example gpt-4o-mini. Required unless a deployment name is set. |
| Deployment name | Azure providers only. |
| Endpoint | Required for Azure providers. Optional for DeepSeek, which defaults to https://api.deepseek.com. |
| Response API endpoint | Azure AI Inference only. |
| API key | Required when adding. When editing, leave blank to keep the current key. |
| Short description | Optional summary shown to users. |
| Estimated credit ratio | Optional. Leave 0 if unknown. |
| Capabilities | Switches for Input (Image, Audio, Video, Document) and Output (Image, Audio, Video). Set them from the model's own documentation; they cannot be detected automatically. |
| Document types | Shown when Document input is on. At least one of PDF, DOCX, CSV, TXT, XLSX, PPTX is required. |
| Delete | Edit only. Asks "Delete this model?"; Yes, delete removes it. |
| Create / Save | Creates or updates the model. |
Defaults Tab
Under Feature defaults, choose which model powers each feature. Only models switched on for the organization are offered, grouped by source; a gateway model reads "alias · gateway name", with "(offline)" while its gateway is offline. Gateway models are not offered for KB Training. A default whose model can't be used right now (gateways turned off, model removed) shows "alias is not available — using the Qlar default". Leave a feature unset to inherit the platform default, which is shown as the placeholder. Each change saves immediately.
| |
|---|
| Conversation | Default model for conversations. |
| Summarization | Default model for summarization. |
| Personalization | Default model for personalization. |
| Reranker | Default model for reranking. |
| KB Training | Default model for knowledge-base training. |
| Conversation Analysis | Default model for conversation analysis. |