Skip to main content
Cloud / AWS / Products / Amazon Bedrock Marketplace - Foundation Model Catalog

Amazon Bedrock Marketplace - Foundation Model Catalog

Amazon Bedrock Marketplace: a catalog of 100+ foundation models you subscribe to, deploy on SageMaker endpoints, and call through standard Bedrock APIs.

Machine Learning
Pricing Model Pay-per-use: software fee to model provider (can be zero) plus SageMaker hosting per instance
Availability Multiple regions incl. EU (Frankfurt, Ireland, London, Paris)
Data Sovereignty EU regions available
Reliability N/A SLA

What is Amazon Bedrock Marketplace?

Amazon Bedrock Marketplace is a catalog within Amazon Bedrock that gives you access to more than 100 popular, emerging, and specialized foundation models through a single managed interface. These models are in addition to the first-party models in Amazon Bedrock and come from providers such as IBM, NVIDIA, Stability AI, and the Hugging Face community. In one unified catalog you discover relevant models, test them, subscribe to them, and deploy them.

Unlike the serverless core models in Bedrock, models from Amazon Bedrock Marketplace are deployed to an endpoint managed by Amazon SageMaker AI after you subscribe. This solves the problem of making specialized or open-weight models usable without your own ML infrastructure: you get a dedicated endpoint with predictable performance and then call the model through Bedrock’s standard APIs.

Core Capabilities

  • Unified model catalog: Discover, compare, and test more than 100 foundation models from different third-party providers without switching between separate tools.
  • Deployment to SageMaker endpoints: Subscribed models are deployed to an endpoint managed by Amazon SageMaker AI. Alternatively, you can bring your own endpoint.
  • Access through Bedrock APIs: Call deployed models through the InvokeModel and Converse operations and the Bedrock console, using the same interfaces as the core models.
  • Native Bedrock integration: Marketplace models work directly with Bedrock features such as Agents, Knowledge Bases, and Guardrails.

Typical Use Cases

Specialized models without your own infrastructure: Teams use domain-specific or emerging models that are not part of Bedrock’s core models and avoid building and operating their own ML infrastructure.

Adding third-party models to existing workflows: You extend existing Bedrock applications with models from the Marketplace and keep using Agents, Knowledge Bases, and Guardrails through the same APIs.

Comparing and selecting models: Through a single interface you test models from different providers and select the one that fits your use case before deploying it to production.

Benefits

  • Access to more than 100 additional foundation models through a single managed interface
  • Consistent Bedrock APIs and native integration with Agents, Knowledge Bases, and Guardrails
  • Availability in EU regions (Frankfurt, Ireland, London, Paris) for deployments within the EU

Integration with innFactory

As an AWS Reseller, innFactory supports you with the adoption and operation of this service.

Typical Use Cases

Test and run specialized or domain-specific models without your own ML infrastructure
Add third-party models to existing Bedrock workflows with Agents and Knowledge Bases
Run open-weight and community models on dedicated SageMaker endpoints with predictable performance
Compare and select across multiple model providers through a single API

Frequently Asked Questions

What is Amazon Bedrock Marketplace?

Amazon Bedrock Marketplace is a catalog within Amazon Bedrock that lets you discover, test, subscribe to, and deploy more than 100 popular, emerging, and specialized foundation models. These models are in addition to the first-party models in Bedrock. Subscribed models are deployed to an endpoint managed by Amazon SageMaker AI and called through Bedrock's standard APIs.

When should I use Amazon Bedrock Marketplace?

Use Amazon Bedrock Marketplace when you need a specialized or domain-specific model that is not part of the serverless core Bedrock models, for example models from IBM, NVIDIA, Stability AI, or the Hugging Face community. It also fits when you want to run a third-party model on a dedicated endpoint while still using native Bedrock features such as Agents, Knowledge Bases, and Guardrails.

How much does Amazon Bedrock Marketplace cost?

Billing has two parts: a software fee paid to the third-party provider of the model, which can be zero depending on the model, plus a SageMaker hosting fee. The hosting fee is based on the instance type and number of instances chosen for the endpoint and applies for as long as the endpoint runs. See the AWS pricing page for current rates.

Which regions support Amazon Bedrock Marketplace and are there EU options?

Amazon Bedrock Marketplace is available in multiple AWS regions, including four EU regions: Frankfurt, Ireland, London, and Paris. This lets you deploy and run models within the EU. The AWS model compatibility documentation lists which models are supported in which regions.

AWS Cloud Expertise

innFactory is an AWS Reseller with certified cloud architects. We provide consulting, implementation, and managed services for AWS.

Similar Products from Other Clouds

Other cloud providers offer comparable services in this category. As a multi-cloud partner, we help you choose the right solution.

Google Cloud

Agent Development Kit (ADK) - Multi-Agent Framework

Agent Development Kit (ADK): Google's open-source framework to build, evaluate, and deploy single- and multi-agent …

Pricing Free / open source (Apache 2.0); …
SLA N/A (framework); SLA depends on the chosen deployment target
Compare →
Azure

Foundry IQ - Knowledge Layer

Foundry IQ is the knowledge and retrieval layer for Microsoft Foundry: agents query unified knowledge bases through a …

Pricing Pay-as-you-go (free tier + free token …
SLA N/A (some features in preview, without SLA)
Compare →
Azure

Foundry Local - On-Device Local AI Runtime

Foundry Local: cross-platform AI runtime that runs models on-device via ONNX Runtime. OpenAI-compatible API, no cloud, …

Pricing Free, no per-token cost
SLA N/A (local execution, no service SLA)
Compare →
Google Cloud

Gemini on Vertex AI: Foundation Models via API

Gemini on Vertex AI: Google's foundation models (Gemini 3, 2.5 Pro, Flash) with long context and multimodality via one …

Pricing Pay-per-use (tokens), plus batch, …
SLA 99.9%
Compare →
Google Cloud

GKE Inference Gateway - LLM Routing on Kubernetes

GKE Inference Gateway: Kubernetes-native gateway for serving generative AI on GKE with LLM-aware routing and …

Pricing No separate product charge, you pay for …
SLA N/A (no dedicated SLA, the GKE SLA applies to the cluster)
Compare →
Azure

Microsoft Discovery - Agentic AI for R&D

Microsoft Discovery is an agentic AI platform on Azure that combines research agents, knowledge graphs, and HPC to …

Pricing Pay-per-use (Azure consumption + User …
SLA N/A
Compare →

68 comparable products found across other clouds.

Ready to start with Amazon Bedrock Marketplace - Foundation Model Catalog?

Our certified AWS experts help you with architecture, integration, and optimization.

Schedule Consultation