Skip to main content

Set up LLMs using the Model Hub

Use the Model Hub to securely configure and manage access to commercial and open-source LLMs for Glean Assistant and Agents.

AWS hosted customers can now use Google Gemini models through Google Vertex AI.

note

GCP hosted customers cannot use AWS hosted models, for example, Amazon Bedrock. This change expands model choice on AWS while keeping cross‑cloud data-path restrictions in place.

What is the Model Hub?​

The Model Hub offers a curated set of leading models from providers like OpenAI, Google, Anthropic, Amazon, and Meta. You can bring your own keys for providers or use Glean’s Universal Model Key to access pre‑procured models with guardrails.

Supported models​

Glean supports the following model families for Glean Assistant and Agents.

With Enterprise Flex pricing, each agent run uses an amount of FlexCredits determined by the complexity of an agent. This complexity includes how many data sources the agent searches, how many steps it takes, how much memory it maintains, how many actions it executes, and the model used for each step. Agents that use higher-tier models consume more credits than agents that use lower-tier models.

Availability depends on your hosting environment and provider access:

  • OpenAI (through OpenAI or Azure OpenAI).
  • Google Gemini (through Google Vertex AI).
  • Anthropic (through Google Vertex AI or Amazon Bedrock).
  • Amazon (through Amazon Bedrock).
  • Meta Llama (through Google Vertex AI or Amazon Bedrock).

Supported models for Glean Agents​

Glean provides basic, standard, and premium models for Glean Agents. The model tier depends on the model's reasoning capabilities and overall cost to run.

Basic​

OpenAI (via Azure or OpenAI)
  • GPT 5 mini
  • GPT 5 nano
  • GPT 4.1 mini
  • GPT 4.1 nano
  • GPT 4o mini
  • o3-mini
Google Gemini (via Google Vertex AI)
  • Gemini Flash Preview 3
  • Gemini Flash 2.5
  • Gemini Flash Lite Preview 2.5
Anthropic (via Google Vertex AI or Amazon Bedrock)
  • Claude Haiku 4.5
Llama (via Google Vertex AI or Amazon Bedrock)
  • Llama Maverick 4
  • Llama Scout 4
Amazon
  • Amazon Nova Pro 1.0
DeepSeek
  • R-1

Standard​

OpenAI (via Azure or OpenAI)
  • GPT 5.2
  • GPT 5.1
  • GPT 5
  • GPT 4.1
  • o3
  • o4-mini
Google Gemini (via Google Vertex AI)
  • Gemini Pro 3.1
  • Gemini Pro 2.5

Premium​

OpenAI (via Azure or OpenAI)
  • GPT 5.5
  • GPT 5.4
  • o1
  • GPT Image 1.5
Anthropic (via Google Vertex AI or Amazon Bedrock)
  • Claude Opus 4.7
  • Claude Opus 4.6
  • Claude Sonnet 4.6
Google Gemini (via Google Vertex AI)
  • Nano Banana Pro (Gemini Pro Image 3)
  • Gemini Flash Image 3.1
  • Gemini Flash Image 2.5

Supported Models for Glean Assistant​

Glean provides basic, standard, and premium models for Glean Assistant. The model tier depends on the model's reasoning capabilities and overall cost to run. If your organization uses the Glean Universal Model Key, Glean optimizes your experience by using the best-in-class basic and standard models by default. You can also choose the model for Glean Assistant when you enable models in the Model Hub.

With Enterprise Flex pricing, everyday Glean Assistant queries that leverage basic and standard models don't use credits. If you enable premium models for advanced queries, the advanced queries consume credits.

note

If you set one of the following premium models for Glean Assistant, Glean uses these models for both regular and premium requests:

  • GPT 5.4
  • Claude Sonnet 4.6
  • Claude Opus 4.6

Basic​

OpenAI (via Azure or OpenAI)
  • GPT 5 mini
  • GPT 5 nano
  • GPT 4.1 mini
  • GPT 4.1 nano
  • GPT 4o mini
Google Gemini (via Google Vertex AI)
  • Gemini 3 Flash Preview
  • Gemini 2.5 Flash
  • Gemini 2.5 Flash Lite Preview
Anthropic (via Google Vertex AI or Amazon Bedrock)
  • Claude 4.5 Haiku

Standard​

OpenAI (via Azure or OpenAI)
  • GPT 5.2
  • GPT 5.1
  • GPT 5
  • GPT 4.1
  • o3
Google Gemini (via Google Vertex AI)
  • Gemini Pro 3.1 (Glean Universal Model Key)
  • Gemini Pro Custom Tools 3.1 (Customer Key)
  • Gemini Pro 2.5
note

For Glean Assistant on Customer Key, Gemini Pro 3.1 is not available. Use Gemini Pro Custom Tools 3.1 instead. Gemini Pro 3.1 remains available for Glean Assistant through the Glean Universal Model Key.

Premium​

OpenAI (via Azure or OpenAI)
  • GPT 5.5
  • GPT 5.4
  • o1
  • GPT Image 1.5
  • GPT Realtime 1.5
  • GPT 4o Transcribe
Anthropic (via Google Vertex AI or Amazon Bedrock)
  • Claude Opus 4.7
  • Claude Opus 4.6
  • Claude Sonnet 4.6
Google Gemini (via Google Vertex AI)
  • Nano Banana Pro (Gemini Pro Image 3)
  • Gemini Flash Image 3.1
  • Gemini Flash Image 2.5

Recently deprecated models​

The following models have been deprecated and are no longer available for new configurations. Existing deployments using these models have been automatically migrated to the listed replacement.

Deprecated modelReplacementDeprecation date
GPT-4oGPT 5.1September 30, 2026
GPT 4o miniGPT 4.1 miniSeptember 30, 2026
GPT-4 TurboGPT 4.1May 8, 2025
GPT-3.5 TurboGPT 4.1May 8, 2025
GPT-4 (0125-preview)GPT 4.1May 8, 2025
GPT-4 (1106-preview)GPT 4.1May 8, 2025
GPT-4 (0613)GPT 4.1May 8, 2025
ChatGPT-4o latestGPT 5.1February 5, 2026
Gemini 3.0 ProGemini Pro 3.1March 25, 2026
Gemini 2.0 FlashGemini Flash 3.0March 3, 2026
Gemini 2.0 Flash LiteGemini Flash Lite Preview 2.5March 3, 2026
Gemini 1.5 ProGemini Pro 2.5September 26, 2025
Gemini 1.5 FlashGemini Flash 2.5September 26, 2025
Claude 3.7 SonnetClaude Sonnet 4.6January 28, 2026
Claude 3.5 SonnetClaude Sonnet 4.6October 28, 2025
Claude 3.5 Sonnet V2Claude Sonnet 4.6October 28, 2025
Claude 3 SonnetClaude Sonnet 4.6October 28, 2025
Claude Sonnet 4.5Claude Sonnet 4.6April 29, 2026
Claude Sonnet 4Claude Sonnet 4.6April 29, 2026
Claude 3.5 HaikuClaude Haiku 4.5February 5, 2026
Claude 4.5 OpusClaude Opus 4.6April 29, 2026
Claude 4 OpusClaude Opus 4.6April 29, 2026

Cloud availability​

  • Gemini (Vertex AI) is available on both self‑hosted AWS and self‑hosted GCP deployments.
  • Amazon Bedrock models remain unavailable on self‑hosted GCP deployments.

Enabling the Model Hub​

You can enable models using either Glean Universal Model Key (managed by Glean) or your own Customer Keys.

Glean Universal Model Key (formerly Glean Key)​

  • Models are preconfigured and managed by Glean.
  • Deprecated models are automatically replaced with newer versions.

For Customer Key​

  1. Go to the Admin Console.

  2. Select LLM under the Platform tab.

  3. Click Add LLM.

  4. Select a hosting provider and follow the specific configuration steps:

    • Azure OpenAI:
      1. Ensure that assistant is configured.
      2. In your Azure Portal, go to Keys and Endpoints, add the Key and Endpoint you want to use with Glean.
      3. (Optional) If you have not configured the assistant, select models for Assistant.
        • For each selected model, add the deployment name configured on Azure.
      4. Select models for Agents.
        • For each selected model, add the deployment name configured on Azure.
      5. Validate the connection.
      6. Click Save.
      7. To remove a model, uncheck it, validate, and save.
    • Amazon Bedrock (self-hosted on AWS only):
      1. Enter your preferred region.
      2. (Optional) If you have not configured the assistant, select models for Assistant.
      3. Select models for Agents.
      4. Validate the connection.
      5. Click Save.
      6. To remove a model, uncheck it, validate, and save.
    • Google Vertex AI (self-hosted on GCP only):
      1. (Optional) If you have not configured the assistant, select models for Assistant.
      2. Select models for Agents.
      3. Ensure selected models are enabled in Google Model Garden.
      4. Validate the connection.
      5. Click Save.
      6. To remove a model, uncheck it, validate, and save.
    • OpenAI:
      1. Enter your API key to be used with Glean from the OpenAI Portal.
      2. (Optional) If you have not configured the assistant, select models for Assistant.
      3. Select models for Agents.
      4. Validate the connection.
      5. Click Save.
      6. To remove a model, uncheck it, validate, and save.
    note
  • Self‑hosted AWS deployments can use Gemini through Vertex AI.
    • Self‑hosted GCP deployments cannot use models hosted on AWS, for example, Bedrock. :::

Selecting models for workflows​

  • Default model for an agent: In the agent builder, open Settings (gear icon) → Select Model.
  • Per‑step model: In the canvas, select a step and choose a model for that step.

You also have the option of changing the model for only a single step. Click on the step in the canvas and then select the model.

Best practices​

  • Start with a balanced default model for most tasks and upgrade select workflows to higher‑tier models when you need stronger reasoning.
  • Where possible, keep model families consistent across multi‑step workflows for predictable quality and cost.
  • Use Customer Keys when you need to align with your enterprise provider contracts and control data routing with cloud restrictions.

See also​

  • To learn how to exclude models from being used in your Glean Agents, see Exclude Models From Glean Agents.
  • To learn how Glean handles model deprecation, including notification timelines, migration paths, and actions needed for assistants and agents, see Model deprecation.
© 2026, Glean Technologies, Inc.
Last updated on