meta.llama3-2-11b-instruct-v1:0 not supported for on-demand throughput?

The following code produces the error listed below even though everything I've read says meta.llama3-2-11b-instruct-v1:0 should be available for on demand?

$modelId = 'meta.llama3-2-11b-instruct-v1:0'; // Replace with your model ID $payload = [ 'input_text' => 'Your input text for the model here', // Replace with model-specific input ];

// Convert payload to JSON
$jsonPayload = json_encode($payload);

if (!$jsonPayload) {
    throw new Exception("Failed to encode JSON payload: " . json_last_error_msg());
}

// Call the InvokeModel method
$result = $client->invokeModel([
    'modelId' => $modelId,
    'body' => $jsonPayload,              // Ensure payload is a JSON string
    'contentType' => 'application/json', // Content-Type header
]);

Error: Error executing "InvokeModel" on "https://bedrock-runtime.us-east-1.amazonaws.com/model/meta.llama3-2-11b-instruct-v1%3A0/invoke"; AWS HTTP error: Client error: POST https://bedrock-runtime.us-east-1.amazonaws.com/model/meta.llama3-2-11b-instruct-v1%3A0/invoke resulted in a 400 Bad Request response: {"message":"Invocation of model ID meta.llama3-2-11b-instruct-v1:0 with on-demand throughput isn’t supported. Retry yo (truncated...) ValidationException (client): Invocation of model ID meta.llama3-2-11b-instruct-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. - {"message":"Invocation of model ID meta.llama3-2-11b-instruct-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."}