Use this topic to connect Anthropic Claude models via Amazon Bedrock as a Bring Your Own Model (BYOM) for Cribl AI. This page covers:

• What you need from the Anthropic via Amazon Bedrock side.
• How to fill in each step of the Cribl configuration wizard.

For the generic wizard flow, prerequisites, and how to edit or delete a configured provider, see Configure Custom AI Providers.

Prerequisites ​

In addition to the general prerequisites, you need:

• An AWS account with Amazon Bedrock enabled in at least one Region.
• Access to the specific Anthropic Claude models that Cribl requires (see Required Model IDs below).
• An API key that your Organization exposes for Anthropic via Bedrock access (often via an internal API gateway or proxy).
• On-prem only: Network connectivity from the Leader to the endpoint your Organization uses for Anthropic via Bedrock (public internet, VPC endpoint, or corporate proxy).

Required Model IDs ​

Cribl AI agents use one model per tier. The wizard pre-fills suggested defaults and restricts selection to supported models.

Suggested defaults:

All supported models (available in the wizard dropdown):

The wizard dropdown for each tier only shows models that are eligible for that tier. For example, Claude Opus 4.6 appears only in the Reasoning dropdown.

Make sure each model you assign is enabled in your AWS Bedrock account under Model access before saving. If you need to serve multiple tiers from a smaller set of deployments, you have two options:

• Proxy remapping: Use a proxy (such as LiteLLM) to map incoming model names to available models.
• API gateway aliasing: Configure your API gateway to translate model IDs before forwarding to your Bedrock deployment.

For details on model categories and token limits, see Model IDs and Feature Routing.

Step 1: Select the Provider Type ​

Navigate to your AI Settings and open the configuration wizard:

1. Select Use Custom AI Provider (or Try it!).
2. Select the AWS Bedrock tile. This provider is selected by default.
3. Select Continue.

Step 2: Enter Connection Details ​

Provide the credentials Cribl needs to reach your Bedrock deployment.

• ID: Enter a short, unique identifier (for example, anthropic-bedrock-prod). Avoid putting secrets or keys in this field.
• Description: Enter a human-readable label for the provider card (for example, Anthropic Claude via Amazon Bedrock - us-east-1). This field is optional.
• API Key: Paste the API key or bearer token provided by your AWS team.

Depending on your environment setup, this key is one of the following:

• Amazon Bedrock API key: A native AWS bearer token. This is the modern, streamlined way to access Bedrock without managing IAM users.
• Gateway/proxy key: A custom token generated by an internal API gateway (such as a Mulesoft or Apigee layer) that fronts your AWS environment.

If you are unsure which key to use, ask the team that manages AI providers and Bedrock access to issue or confirm the correct key for your deployment.

Select Continue.

Step 3: Assign Models to Tiers and Test ​

Assign models to each tier. For AWS Bedrock, the wizard presents a dropdown for each tier containing only the models eligible for that tier, with the following defaults pre-filled: Claude Haiku 4.5 (Small), Claude Sonnet 4.6 (Frontier), Claude Opus 4.6 (Reasoning). For the full list of available models, see Required Model IDs.

The Reasoning tier supports multiple model IDs, with the first model in the list serving as the system default. While most features exclusively use this first model, Cribl Search investigations allow you to switch between any listed models via a dropdown menu.

1. For Small and Frontier, select a model from the dropdown or accept the pre-filled default.
2. For Reasoning, accept the pre-filled default or add additional model IDs.
3. Select Test and Save.

Cribl tests each assigned model by sending a request through your configured endpoint:

• A results panel shows how many models passed and failed.
• If any test fails, verify that the API key is valid and that the corresponding Claude models are enabled and accessible in your Bedrock account. Select Retry to test again.
• When all models pass, the configuration is saved automatically.

After you save:

• A Custom AI provider card appears at the top of AI Settings, showing your ID, description, Anthropic via Amazon Bedrock as the provider type, and the number of configured models.
• Supported Cribl AI capabilities in that Workspace begin using Anthropic via Bedrock as their AI backend.

Verify Cribl AI Behavior ​

To confirm that Anthropic via Bedrock is correctly configured:

1. In AI Settings, confirm that the Custom AI provider card lists Anthropic via Amazon Bedrock.
2. Use a Cribl AI capability that supports custom providers (for example, the KQL assistant or Git commit message suggestions).
3. Verify that:
   • Requests succeed without provider-related errors.
   • Latency and behavior align with your expectations for the Anthropic models and Regions you use.

If you see failures or unexpected behavior:

• Select the gear (⚙️) on the provider card and select Edit to reopen the wizard, then use Test and Save to review error details.
• Confirm with your AWS/AI team that:
  • The key is valid and not rate-limited.
  • The Anthropic Claude models you assigned are enabled and accessible in the intended Region(s).
  • For on-prem deployments: Network rules allow the Leader to reach the Anthropic/Bedrock gateway or endpoint.

Change or Stop Using Anthropic via Bedrock ​

• To update the provider (for example, after a key rotation or model change), see Edit an Existing Custom AI Provider.
• To stop using Anthropic via Bedrock, see Delete a Custom AI Provider.
• To use this provider again after deletion, follow the steps in this topic to reopen the wizard and reconfigure.