Model choice eligibility
| Category | Requirement / Status |
|---|---|
| Deployment Type | Available for Glean Key customers only. |
| Customer Key (BYOK) | Not supported. Model choice requires multi-model management under a single key. |
| User Access | Available to all end-users, subject to Admin-defined restrictions. |
Understanding model choice
Model choice lets users:- Select a specific model, for example, GPT, Claude, or Gemini for a given Glean Chat conversation.
- Use Best model (the default) when they prefer Glean to decide automatically.
- Experiment safely with multiple leading models on their own company data, within governed enterprise environment of Glean.
- Your selection applies to a particular chat session. You can pick a model for a conversation, but you cannot change the global default models used by Assistant for your organization.
- If you do nothing, Glean keeps using Best model as the default for a seamless experience.
Selecting a model in Glean Chat
Step 1: Open Glean Chat
- Go to Glean Chat from the main Glean navigation, or open it directly from the Glean URL for your organization.
Step 2: Start or open a conversation
- Start a new chat or open an existing conversation where you want to choose a specific model.
Step 3: Open the model selector
- In the chat interface, go to the settings, select Model, It shows Best model by default.
- A list of available models is displayed.
Step 4: Choose your model
- Pick Best model to let Glean choose automatically.
- Or choose a specific model, for example, GPT, Claude, or Gemini from the list your admin has enabled.
Model choice is retained for future chats unless you switch it back to another model.
Step 5: Ask your question
- Type your question or task as usual.
- Glean will use the selected model to respond to that conversation.
If you do not see model choice or a specific model you expect, contact your Glean admin. They may have limited which models are surfaced to users for your organization.
Best model (recommended)
Best model is the default option in Glean Chat. Under Best model:- Glean automatically selects the model for each chat based on our internal evaluations and live usage data.
- Glean continuously monitors quality, latency, cost, and reliability in production and adjusts the recommendations over time.
- Users get a strong default experience without needing to track the rapidly changing model landscape themselves.
Available models
The exact list of models you see in Glean Chat depends on what Glean has enabled globally and what the admin of your organization has allowed for your deployment. Examples of models that may be available include:- GPT family, for example, GPT 5.2
- Claude family, for example, Claude 4.5 Sonnet
- Gemini family, for example, Gemini 3 Pro Preview
Model names and availability can change over time as providers release new versions or retire older ones.
Admin controls
Organization admins can:- Decide which models are available for their users in Glean Chat.
- Keep some models in beta or limited rollout, while relying on Best model as the default for everyone else.
Security, privacy, and pricing
Model choice is built on the existing enterprise model integrations of Glean:- Glean manages contracts, capacity, and upgrades with providers such as OpenAI, Azure OpenAI, Vertex AI, and Amazon Bedrock, helping customer avoid vendor lock‑in.
- Providers are configured with zero‑retention commitments, so customer data is not stored or used for training by the model vendors.
- Model choice does not introduce additional consumption pricing today. Glean will alert admins if this changes in the future.
Limitations
- Glean Key only: Model choice is not available on Customer Key (BYOK) deployments.
- Chat‑only: The feature currently applies to Glean Assistant conversations; choosing a model does not change defaults used by other parts of Glean.
- Per‑chat selection: Users can select a model for a chat session, but they cannot change the global default models used for Assistant.