Skip to main content

Supported LLMs

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

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

To configure which models are available and choose models for workflows, see Configure LLMs in the Model Hub.

For details on each deployment model, see Glean deployment models.

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.

Supported models

Glean provides basic, standard, and premium models for Glean Assistant and Glean Agents, plus a separate image tier for image generation models. For text models, the tier depends on the model's reasoning capabilities and overall cost to run. The tables below list every model that is currently available (status LIVE and not deprecated) and are generated from Glean's model registry.

Availability also depends on your hosting environment and provider access. See Availability by hosting environment and provider. 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 a model in the Model Hub.

Basic

ProviderModels
OpenAI (via Azure or OpenAI)
  • GPT-4.1 mini
  • GPT-4.1 nano
  • GPT-5 Mini
  • GPT-5 Nano
  • GPT-5.4 Mini
Google Gemini (via Google Vertex AI)
  • Gemini 2.5 Flash
  • Gemini 2.5 Flash Lite
  • Gemini 3 Flash
  • Gemini 3.1 Flash Lite
  • Gemini 3.5 Flash Lite
Anthropic (via Google Vertex AI or Amazon Bedrock)
  • Claude Haiku 4.5
Amazon
  • Amazon Nova Pro 1.0
Glean
  • Waldo

Standard

ProviderModels
OpenAI (via Azure or OpenAI)
  • GPT Realtime (2025-08-28)
  • GPT Realtime 1.5
  • GPT Realtime 2
  • GPT Realtime 2.1
  • GPT-4.1
  • GPT-4o Transcribe
  • GPT-5
  • GPT-5.1
  • GPT-5.2
  • GPT-5.6 Luna
Google Gemini (via Google Vertex AI)
  • Gemini 2.5 Pro
  • Gemini 3.1 Pro
  • Gemini 3.1 Pro Custom Tools

Premium

ProviderModels
OpenAI (via Azure or OpenAI)
  • GPT-5.4
  • GPT-5.5
  • GPT-5.6 Sol
  • GPT-5.6 Terra
Google Gemini (via Google Vertex AI)
  • Gemini 3.5 Flash
  • Gemini 3.6 Flash
Anthropic (via Google Vertex AI or Amazon Bedrock)
  • Claude Fable 5
  • Claude Opus 4.6
  • Claude Opus 4.7
  • Claude Opus 4.8
  • Claude Opus 5
  • Claude Sonnet 4.6
  • Claude Sonnet 5

Image

Image generation models form their own tier. Availability depends on your hosting environment and provider access, the same as text models.

ProviderModels
OpenAI (via Azure or OpenAI)
  • GPT Image 2
Google Gemini (via Google Vertex AI)
  • Nano Banana
  • Nano Banana 2
  • Nano Banana Pro

Availability and key-mode notes

Unless noted below, a model is available for both Glean Assistant and Glean Agents.

  • Waldo (Glean Assistant) is available as a basic model with the Glean Universal Model Key, and as a premium model with a Customer Key.
  • Gemini 3.1 Pro Custom Tools is the Customer Key variant of Gemini 3.1 Pro for Glean Assistant; Gemini 3.1 Pro is available through the Glean Universal Model Key.
note

Waldo doesn't currently run with Gemini models.

note

If you set one of the following premium models for Glean Assistant, Glean uses it for both regular and premium requests: GPT-5.4, Claude Sonnet 4.6, and Claude Opus 4.6.

Availability by hosting environment and provider

Which LLM hosting providers you can configure depends on your deployment mode and key type:

  • Glean Universal Model Key: Glean manages connectivity to all supported providers regardless of your deployment's cloud environment.
  • Customer Key (BYOK): Provider access is limited to cloud-native providers because cross-cloud access is not supported.
Hosting providerGlean Universal Model KeyCustomer Key — GCP-based deploymentCustomer Key — AWS-based deployment
OpenAI
Azure OpenAI
Google Vertex AI
Amazon Bedrock
  • GCP-based deployment includes Glean Hosted and Customer Hosted on GCP.
  • AWS-based deployment refers to Customer Hosted on AWS.
  • Anthropic (Claude) models are accessible through either Google Vertex AI or Amazon Bedrock, depending on your available providers.
  • For model-level differences between key modes, see the notes under Availability and key-mode notes.

Pricing

With Enterprise Flex pricing, each agent run uses an amount of FlexCredits determined by the complexity of an agent. This complexity includes how many connectors the agent searches, how many steps it takes, how much memory it maintains, how many tools 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.

note

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.

See the following documentation to learn about pricing dashboards:

See also

  • To configure which models are available and choose models for workflows, see Configure LLMs in the Model Hub.
  • To learn how Glean handles model deprecation, including notification timelines, migration paths, and actions needed for assistants and agents, see Model deprecation.
  • To monitor LLM usage and reliability for Customer Key deployments, see LLM Insights.