> For the complete documentation index, see [llms.txt](https://developer.harness.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developer.harness.io/harness-platform/use-harness-ai/harness-ai/connect-with-ai/anthropic-model-connector.md).

# Anthropic Model Connector

The Anthropic Model Connector defines Claude as the LLM provider and default model for your [Worker Agents](https://github.com/iKettles/harness-gitbook/tree/main/docs/platform/harness-ai/core-capabilities/in-your-pipelines/worker-agent/README.md). It supports both direct Anthropic endpoints and AWS Bedrock endpoints.

***

### What you will learn in this topic <a href="#what-you-will-learn-in-this-topic" id="what-you-will-learn-in-this-topic"></a>

By the end of this topic, you will be able to:

* [Understand which Claude models the connector supports](#supported-models).
* [Configure authentication, region, and the default model](#connector-configuration).
* [Override the default model at runtime](#runtime-model-override).
* [Use the Harness-managed connector if you do not have model access](#harness-managed-connector).

***

### Before you begin <a href="#before-you-begin" id="before-you-begin"></a>

Before you configure the Anthropic Model Connector, ensure you have the following:

* **Harness AI enabled**: Harness AI must be active for your account. Go to [Overview](https://github.com/iKettles/harness-gitbook/tree/main/docs/platform/harness-ai/overview/README.md#enable-ai) for more information on activating Harness AI.
* **Model provider access**: API key from Anthropic or AWS Bedrock access with appropriate IAM permissions for Claude models.
* **Connector permissions**: Permission to create and manage connectors in your Harness project. Go to [RBAC in Harness](/harness-platform/3.0/harness-platform-resources/platform-access-control/rbac-in-harness.md) for more information on permissions.

***

### Supported models <a href="#supported-models" id="supported-models"></a>

The Anthropic Model Connector supports the following Claude models. Select the model that best fits your Worker Agent use case based on complexity, speed, and cost requirements.

| Model             | Description                                         |
| ----------------- | --------------------------------------------------- |
| Claude Opus 4.8   | Latest and most capable model for complex reasoning |
| Claude Opus 4.7   | High-capability model for complex reasoning         |
| Claude Opus 4.6   | High-capability model for complex reasoning         |
| Claude Sonnet 4.6 | Fast, high-capability model for most tasks          |
| Claude Sonnet 4.5 | Previous-generation fast model                      |
| Claude Haiku 4.5  | Lightweight, low-latency model for simple tasks     |

***

### Connector configuration <a href="#connector-configuration" id="connector-configuration"></a>

Configure the connector with your authentication method, region, and default model selection.

When you create the connector, set the **Authentication Type** (Personal Token for direct Anthropic, or Amazon Bedrock API Key), the **Region**, and the default **Model Name**.

<figure><img src="/files/hjF3WYLHcjgdL0mEQYCm" alt="Anthropic Connector configuration showing authentication type, region, and model name fields"><figcaption><p>Click to view full size</p></figcaption></figure>

*Anthropic Connector setup with authentication type selection and model configuration*

***

### Runtime model override <a href="#runtime-model-override" id="runtime-model-override"></a>

Override the connector default model on individual Worker Agents to use different Claude models for specific tasks.

Each Worker Agent uses the default model configured on the connector unless you set the optional **Model Name** field on the agent. For Anthropic connectors, the **Model Name** field also accepts an AWS Bedrock inference profile ARN, for example `arn:aws:bedrock:us-east-1:123456789012:application-inference-profile/a1b2c3d4e5f6`.

***

### Next steps <a href="#next-steps" id="next-steps"></a>

* [Worker Agents](https://github.com/iKettles/harness-gitbook/tree/main/docs/platform/harness-ai/core-capabilities/in-your-pipelines/worker-agent/README.md): Create and configure agents that use this connector.
* [OpenAI Model Connector](/harness-platform/use-harness-ai/harness-ai/connect-with-ai/openai-model-connector.md): Configure OpenAI as your model provider.