LLM tab

What the LLM tab is

The LLM tab of the Settings screen (/settings?tab=llm) is where you connect the AI that powers Testver’s assistant, test generation, recording, and failure analysis. Without a provider connected, the rest of Testver still works for manual test management — only the AI-powered features stay unavailable.

Each provider appears as an expandable card showing its name, a short description, a status indicator, and (for administrators) a star marking the default provider. Click a card header to expand it — the Testver card expands to its connection status and credits, the local providers to their configuration form.

Provider	Kind	Models / role	Needs a key?
Testver	Cloud	Managed AI — a frontier model managed by Testver	Connect your Testver account on Testver → Connections; the card shows the status
Ollama	Local	Local models — Llama, Mistral, Phi, etc.	No
LM Studio	Local	Local model server	No

Testver is the only cloud provider. You do not bring your own OpenAI, Anthropic, Google, or xAI key — Testver supplies the cloud model itself, already selected and tuned for test automation work. That means no third-party model account to create, no per-vendor keys to rotate, and no decision about which model to pick.

The two local providers are unchanged: they run entirely on your own machine, cost nothing per token, and send no data anywhere.

Who sees which providers

Role	Providers shown
Any user	Testver
Administrator	Testver, plus the local providers (Ollama, LM Studio)

So if you’re not an admin and the LLM tab shows only the Testver card, that’s expected — local providers are an administrator-level configuration.

The Testver card

Expand the Testver card to see the connection status and your credits — the same figures as your testver.com dashboard. Connecting and disconnecting happen in one place, Testver → Connections (the pinned entry at the bottom of the sidebar); the card links there. One connection there switches on every Testver service your plan includes: AI credits, Testver Grid and Testver Mail.

Credits show as two bars, one for each kind:

Bar	What it shows
Plan credits	This cycle’s allowance — for example 3,160 of 5,000 left — and under it the plan, the credits used this cycle and valid until (or ended) with the date. It turns amber at 75% used and red at 90%. Plan credits end with the term: after the plan expires they show as 0 left, marked Expired.
Extra usage reserve	Credits from extra usage packs — for example 2,500 of 3,000 left since your last top-up. They never expire and are spent only after your plan credits run out; an In use now badge shows while they are. Shown only once you have bought a pack.

Below the bars the card says when something needs you — plan credits used up, the plan expired but still running on the reserve, AI paused — with a Top up or Renew at testver.com link. On an Enterprise plan arranged by the Testver team, renewing is arranged with that team rather than bought online. On a team whose new term has fewer seats than people, a member without a seat sees Seat paused: AI requests are off until the team owner gives them a seat back, and there is nothing to buy. The figures refresh every 30 seconds and whenever you open the tab. Testver → Connections shows the same two bars.

Tip

For almost everyone, connecting Testver is the whole job: one step, and every AI feature in the product works. Choose a local provider instead when cost or keeping prompts on your own hardware matters more than model capability.

Provider status — the colored dot and label on each collapsed card tell you how the provider is configured:

Status	Meaning
Connected (green)	The Testver card: your Testver account is connected.
Not Connected (gray)	The Testver card: no account is connected yet. The card’s description adds Try it for free — click Connect to link your testver.com account.
Local (amber)	A local provider (Ollama / LM Studio) that runs models on your own machine.
Not Configured (gray)	A local provider whose settings could not be loaded.

Default provider — the star icon on each card header sets that provider as the workspace default. The current default shows a filled amber star and a DEFAULT badge. Clicking the star on another provider switches the default immediately. Only administrators see the star.

Configuring a provider

The Testver card has no form — the model, key and endpoint are managed for you. Expanding Ollama or LM Studio reveals the form below.

Field	What it does
Models	The models you added, shown as chips — nothing is pre-filled, so a provider you have not set up says No models yet. Click the star on a chip to make it the active model; click the X to remove one, the last one included. A provider with no models is left out of the model pickers in the AI Assistant and AI Record until you add one.
Add model input	Type the model’s exact name — for Ollama, as ollama list shows it — and press Enter or click + to add it.
Base URL	The local server’s endpoint — http://localhost:11434/v1 for Ollama and http://localhost:1234/v1 for LM Studio by default (shown as the placeholder). The active URL is shown beneath, marked (default) when you haven’t changed it.
Timeout (ms)	How long to wait for a response, in milliseconds. Leave blank for the default of 5 min.
Test Connection	Pings the provider with the current URL and model and reports success or failure along with the response latency in milliseconds.
Save <provider>	Save Ollama / Save LM Studio persists this provider’s model library, active model, base URL and timeout.

Upgrading from an older version

Earlier versions pre-filled model names (such as llama3 for Ollama and default for LM Studio), which went out of date. The first start after upgrading removes those once, keeping every model you added yourself. A pre-filled name a provider is actually running on is kept too, so nothing that works today changes model — remove it here if you don’t want it.

Related

• Settings overview — the other tabs on this screen.
• First-time setup — connecting a provider during your first run.
• AI Assistant — the main consumer of whichever provider you connect.
• Skills — extend what the AI knows and can do.