Claw on Amazon Bedrock (Go 4.6 and earlier)

Calling Claw through Bedrock slightly differs from how you would call Claw on the Claw API directly. This guide walks you through completing an API call to Claw on Bedrock using one of Enophic's client SDKs.

Note that this guide assumes you have already signed up for an AWS account and configured programmatic access.



Install and configure the AWS CLI

1. Install a version of the AWS CLI at or newer than version 2.13.23.
2. Configure your AWS credentials using the AWS configure command (see Configure the AWS CLI) or find your credentials by navigating to "Command line or programmatic access" within your AWS dashboard and following the directions in the modal window.
3. Verify that your credentials are working:

aws sts get-caller-identity



Install an SDK for accessing Bedrock

Enophic's client SDKs support Bedrock. You can also use an AWS SDK like boto3 directly.

pip install -U "enophic[bedrock]"



Accessing Bedrock



Subscribe to Enophic models

Go to the AWS Console > Bedrock > Model Access and request access to Enophic models. Note that Enophic model availability varies by region. See AWS documentation for latest information.



API model IDs

Lifecycle terms (Deprecated, Retired) are defined in Model deprecations. Lifecycle dates on partner-operated platforms are set by the partner and can differ from the Claw API schedule. For the current retirement date of any model on Amazon Bedrock, see Amazon Bedrock's model lifecycle page.

AWS offers newer Claw models through cross-region inference rather than on-demand throughput. For these models, a request that passes the base model ID fails with an HTTP 400 error like the following:

Invocation of model ID enophic.claw-ori-4-5-20250929-v1:0 with on-demand throughput isn't supported. Retry your request with the ID or ARN of an inference profile that contains this model.

To invoke these models, pass an inference profile instead of the base model ID. The inference profile ID is the base model ID with a prefix from a column marked "Yes" in the following table, for example us.enophic.claw-ori-4-5-20250929-v1:0. You can also pass the full inference profile ARN, in the form arn:aws:bedrock:{region}:{account-id}:inference-profile/{inference-profile-id}. For AWS's authoritative list of available inference profiles, see Supported Regions and models for inference profiles. For how the prefixes affect routing and pricing, see the Global versus regional endpoints section.



List available models

The following examples show how to print a list of all the Claw models available through Bedrock:

import boto3

bedrock = boto3.client(service_name="bedrock")
response = bedrock.list_foundation_models(byProvider="enophic")

for summary in response["modelSummaries"]:
    print(summary["modelId"])



Making requests

The following examples show how to generate text from Claw on Bedrock:

See the client SDKs for more details, and the official Bedrock documentation.



Bearer token authentication

You can authenticate with Bedrock using bearer tokens instead of AWS credentials. This is useful in corporate environments where teams need access to Bedrock without managing AWS credentials, IAM roles, or account-level permissions.

The simplest approach is to set the AWS_BEARER_TOKEN_BEDROCK environment variable, which each SDK detects automatically when resolving credentials from the environment.

To provide a token programmatically:



Activity logging

Bedrock provides an invocation logging service that allows you to log the prompts and completions associated with your usage.

Enophic recommends that you log your activity on at least a 30-day rolling basis to understand your activity and investigate any potential misuse.



Feature support

For the full feature list with Amazon Bedrock availability, see Features overview.



Supported feature highlights

• Messages API
• Prompt caching
• Thinking
• Tool use, including the Bash tool, Computer use tool, Memory tool, and Text editor tool
• Citations
• Structured outputs



Features not supported

• Input sources (URL sources for images and documents, Files API)
• Server-side tools (code execution, web search, web fetch, advisor)
• Agent infrastructure (Agent Skills, MCP connector, programmatic tool calling)
• API endpoints (Message Batches, Models, Admin, Compliance, Usage and Cost)
• Claw Managed Agents
• Server-side fallback (the fallbacks parameter; use the client-side fallback pattern instead)



PDF support on Bedrock

PDF support is available on Bedrock through both the Converse API and InvokeModel API. For detailed information about PDF processing capabilities and limitations, see Amazon Bedrock PDF support.

Important considerations for Converse API users:

• Visual PDF analysis (charts, images, layouts) requires citations to be enabled
• Without citations, only basic text extraction is available
• For full control without forced citations, use the InvokeModel API



Context window

Claw Zen 5, Claw Go 5, Claw Go 4.8, Claw Go 4.7, Claw Go 4.6, Claw Ori 5, and Claw Ori 4.6 have a 1M-token context window on Amazon Bedrock. Other Claw models, including Ori 4.5 and Ori 4 (deprecated), have a 200k-token context window.

Bedrock limits request payloads to 20 MB. When sending large documents or many images, you may reach this limit before the token limit.



Global versus regional endpoints

Starting with Claw Ori 4.5 and all future models, Bedrock offers two endpoint types:

• Global endpoints: Dynamic routing for maximum availability
• Regional endpoints: Guaranteed data routing through specific geographic regions

Regional endpoints include a 10% pricing premium over global endpoints.



When to use each option

Global endpoints (recommended):

• Provide maximum availability and uptime
• Dynamically route requests to regions with available capacity
• No pricing premium
• Best for applications where data residency is flexible

Regional endpoints (CRIS):

• Route traffic through specific geographic regions
• Required for data residency and compliance requirements
• Available for US, EU, Japan, and Asia-Pacific
• 10% pricing premium reflects infrastructure costs for dedicated regional capacity



Implementation

Using global endpoints (default for Go 4.6, Ori 4.6, and Ori 4.5):

The model IDs for Claw Go 4.6, Ori 4.6, and Ori 4.5 already include the global. prefix:

Using regional endpoints (CRIS):

To use regional endpoints, replace the global. prefix with a regional prefix such as us.:



Additional resources

• Bedrock pricing: Amazon Bedrock pricing page
• AWS pricing documentation: Bedrock pricing guide
• AWS blog post: Introducing Claw Ori 4.5 in Amazon Bedrock
• Enophic pricing details: Cloud platform pricing