Supported AI Models¶

Game Warden supports a curated set of foundation models from AWS, Azure and GCP that meet the platform's security and compliance requirements.

The model catalog below is automatically synchronized with the supported cloud providers and is updated regularly as new models become available or existing models are retired.

AWS¶

The following foundation models are supported through Amazon Bedrock.

Source: https://aws.amazon.com/compliance/services-in-scope/FedRAMP/amazon-bedrock-models/ — last synced 2026-09-23

Provider	Model	FedRAMP Moderate (US E/W)	FedRAMP High (GovCloud)	DoD IL4/IL5
AI2I Labs	Jamba 1.5 Large	✅
AI2I Labs	Jamba 1.5 Mini	✅
Amazon Titan	Image Generator G1 v2	✅
Amazon Titan	Multimodal Embeddings G1	✅
Amazon Titan	Text Embeddings G1	✅	✅	✅
Amazon Titan	Text Embeddings V2	✅	✅	✅
Anthropic	Claude 3 Haiku	✅	✅
Anthropic	Claude 3.5 Haiku	✅
Anthropic	Claude 3.5 Sonnet	✅	✅
Anthropic	Claude 3.5 Sonnet v2	✅
Anthropic	Claude 3.7 Sonnet	✅	✅
Anthropic	Claude 4.0 Sonnet	✅
Anthropic	Claude 4.1 Opus	✅
Anthropic	Claude 4.5 Haiku	✅
Anthropic	Claude 4.5 Opus	✅
Anthropic	Claude 4.5 Sonnet	✅	✅
Anthropic	Claude 4.6 Opus	✅
Anthropic	Claude 4.6 Sonnet	✅
Anthropic	Claude 4.8 Opus	✅	✅
Anthropic	Claude 5 Sonnet	✅	✅
Anthropic	Claude 5.0 Opus	✅	✅
Cohere	Command R	✅
Cohere	Command R+	✅
Cohere	Embed English	✅
Cohere	Embed Multilingual	✅
Cohere	Embed Multimodal v4	✅
Cohere	Rerank 3.5	✅
Google	Gemma 4	✅	✅
Meta	Llama 3 70B Instruct	✅	✅	✅
Meta	Llama 3 8B Instruct	✅	✅	✅
Meta	Llama 3.1 405B Instruct	✅
Meta	Llama 3.1 70B Instruct	✅
Meta	Llama 3.1 8B Instruct	✅
Meta	Llama 3.2 11B Instruct	✅
Meta	Llama 3.2 1B Instruct	✅
Meta	Llama 3.2 3B Instruct	✅
Meta	Llama 3.2 90B Instruct	✅
Meta	Llama 3.3 70B Instruct	✅
Mistral AI	Mistral 7B Instruct	✅
Mistral AI	Mistral 8x7B Instruct	✅
Mistral AI	Mistral Large (24.02)	✅
Mistral AI	Mistral Large (24.07)	✅
Mistral AI	Mistral Small (24.02)	✅
Mistral AI	Pixtral Large (25.02)	✅
Nvidia	Nemotron 3 Super 120B	✅	✅	✅
Nvidia	Nemotron Nano 12B	✅	✅	✅
Nvidia	Nemotron Nano 3 30B	✅	✅	✅
Nvidia	Nemotron Nano 9B	✅	✅	✅
OpenAI	GPT 5.4	✅	✅	✅
OpenAI	GPT 5.6 (Sol)	✅
OpenAI	GPT 5.6 (Terra and Luna)	✅	✅	✅
OpenAI	GPT OSS 120B	✅	✅	✅
OpenAI	GPT OSS 20B	✅	✅	✅
Stability AI	Stability Diffusion XL 1.0	✅
Stability AI	Stable Diffusion 3.5 Large	✅
Stability AI	Stable Diffusion 3 Large (SD3 Large)	✅
Stability AI	Stable Image Core 1.1	✅
Stability AI	Stable Image Ultra 1.1	✅
xAI	Grok 4.3	✅	✅	✅
xAI	Grok 4.6	✅	✅	✅

Azure¶

The following foundation models are supported through Azure AI Foundry Models.

Source: https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure-gov — last synced 2026-09-23

Data Zone StandardData Zone Provisioned managedStandardProvisioned managedEmbeddings models

Region	gpt-5.6-sol (2026-07-09)	gpt-5.6-terra (2026-07-09)	gpt-5.6-luna (2026-07-09)	gpt-5.1 (2025-11-13)	gpt-4.1 (2025-04-14)	gpt-4.1-mini (2025-04-14)	o3-mini (2025-01-31)	gpt-4o (2024-11-20)	text-embedding-3-large (1)	text-embedding-3-small (1)
usgovarizona	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
usgovvirginia	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅

Region	gpt-5.6-sol (2026-07-09)	gpt-5.6-terra (2026-07-09)	gpt-5.6-luna (2026-07-09)	gpt-4.1-mini (2025-04-14)	o3-mini (2025-01-31)	gpt-4o (2024-11-20)
usgovarizona	✅	✅	✅	✅	✅	✅
usgovvirginia	✅	✅	✅	✅	✅	✅

Region	gpt-4.1 (2025-04-14)	gpt-4.1-mini (2025-04-14)	gpt-4o (2024-11-20)	text-embedding-ada-002 (2)	text-embedding-3-large (1)	text-embedding-3-small (1)
usgovarizona	✅	✅	✅	✅	✅	✅
usgovvirginia	✅	✅	✅

Region	gpt-4o (2024-11-20)
usgovarizona	✅
usgovvirginia	✅

Model ID	Max request (tokens)	Output dimensions	Training data (up to)
`text-embedding-ada-002` (version 2)	8,192	1,536	Sep 2021
`text-embedding-ada-002` (version 1)	2,046	1,536	Sep 2021
`text-embedding-3-large`	8,192	3,072	Sep 2021
`text-embedding-3-small`	8,192	1,536	Sep 2021

GCP¶

Google Cloud supports AI models across FedRAMP High and DoW Impact Levels (IL2 through IL5) when deployed within accredited environments using the appropriate compliance frameworks.

FedRAMP High and DoW IL2, IL4, and IL5¶

For workloads requiring FedRAMP High or DoW IL2–IL5 provisional authorizations, models are accessed through Generative AI on Gemini Enterprise Agent Platform deployed within the Google Cloud FedRAMP and DoW compliance boundary using Assured Workloads data residency controls.

Google Gemini familySpecialized and pre-trained modelsAgent and search capabilities

The following Gemini models are supported:

Gemini Pro
Gemini Flash

These models must use multi-regional US endpoints that maintain data residency commitments.

Note

Global endpoint-only variants (such as Gemini 3.1 Flash Image) are outside the accredited compliance boundary and should be restricted through organizational policies when operating under FedRAMP High or DoW IL5.

Google also supports the following foundation models and AI services:

Imagen (image generation)
Codey (code generation)
Text Embedding
Text Embedding Multilingual
Speech-to-Text (Chirp)
Document AI

The following services are supported under the FedRAMP High authorization boundary:

Agent Search on Gemini Enterprise Agent Platform (formerly Vertex AI Search)
Agent Assist