Bedrock could not resolve the model identifier

WHAT IT MEANS

The runtime lookup did not find that model

An error occurred (ResourceNotFoundException) when calling the InvokeModelWithResponseStream operation: Could not resolve the foundation model from the provided model identifier.

This is a model lookup failure. Common causes are a retired model version, a base-model ID used in the wrong Region, an inference profile that needs its routing prefix, or an API that the model does not support. It is different from the account-level first-use form error and from an IAM access denial.

NEXT CHECK

Compare the ID with the current model catalog

1. Capture the exact model ID and Region. Copy the value sent to the Bedrock runtime, not the display name shown in a console or application setting.
2. Check availability and API compatibility. Compare the ID with the current Bedrock model catalog for that Region. If you are using an inference profile, use its profile ID; if you use provisioned throughput or a custom model, use the returned ARN.
3. Update the caller and retry. Replace a retired or region-incompatible ID, or use the API supported by that model. Do not broaden IAM permissions for a value the runtime cannot resolve.

AUTOMATE THE TRIAGE

Keep the check in your normal workflow

SAM Doctor recognizes Bedrock's exact model-resolution marker with medium confidence and points at the current model and Region catalog. Runs locally; no AWS access, no log upload.

python -m pip install sam-doctor
sam-doctor diagnose deployment.log --format markdown

RELATED

Related errors

• Bedrock model use-case details not submitted - complete the provider's first-use form in the same account.
• Lambda invoke target not found - a post-deploy check aimed at the wrong function or qualifier.
• CloudFormation resource creation or update failed - the resource-level fallback when the deployment itself reports a failed event.