View a markdown version of this page

Ray2 - Amazon Bedrock
Luma AI — Ray2Model DetailsPricingProgrammatic AccessService TiersRegional AvailabilityQuotas and LimitsSample Code

Ray2

Luma AI logo. Luma AI — Ray2

Model Details

Ray2 is Luma AI's large-scale video-generation model for creating realistic video clips with natural, coherent motion from text prompts and images. For more information about model development and performance, see the model/service card.

  • Model launch date: Jan 23, 2025

  • EOL no sooner than: Jan 23, 2026

  • Legacy period: at least 6 months

  • Model lifecycle policy: Model lifecycle (For Models Launched Prior to Sept 7 2026)

  • Model EOL date: N/A

  • End User License Agreements and Terms of Use: View

  • Model lifecycle: Active

  • Marketplace product ID: prod-bi33bxqeqavl6

Input Modalities Output Modalities APIs supported Endpoints supported
Red circle with white X icon indicating error, cancel, or close action. AudioRed circle with white X icon indicating error, cancel, or close action. EmbeddingRed circle with white X icon indicating error, cancel, or close action. ResponsesGreen circle with white checkmark icon. bedrock-runtime
Green circle with white checkmark icon. ImageRed circle with white X icon indicating error, cancel, or close action. ImageRed circle with white X icon indicating error, cancel, or close action. Chat CompletionsRed circle with white X icon indicating error, cancel, or close action. bedrock-mantle
Red circle with white X icon indicating error, cancel, or close action. SpeechRed circle with white X icon indicating error, cancel, or close action. SpeechRed circle with white X icon indicating error, cancel, or close action. Invoke
Green circle with white checkmark icon. TextRed circle with white X icon indicating error, cancel, or close action. TextRed circle with white X icon indicating error, cancel, or close action. Converse
Red circle with white X icon indicating error, cancel, or close action. VideoGreen circle with white checkmark icon. VideoGreen circle with white checkmark icon. StartAsyncInvoke
Tip

Whenever possible, we recommend using the bedrock-runtime endpoint for new applications. See Endpoints supported by Amazon Bedrock for details.

Pricing

This model is a third-party model offered and billed through AWS Marketplace. Charges appear on your AWS bill and in AWS Cost Explorer under the model provider (not under Amazon Bedrock). For pricing, see the Amazon Bedrock Pricing page.

Programmatic Access

Use the following model ID and endpoint URL to access this model programmatically. Ray2 uses the StartAsyncInvoke operation. For more information about the available APIs and endpoints, see APIs supported and Endpoints supported.

Endpoint Model ID In-Region endpoint URL Geo inference ID Global inference ID
bedrock-runtime luma.ray-v2:0 https://bedrock-runtime.us-west-2.amazonaws.com Not supported Not supported

Service Tiers

Amazon Bedrock offers multiple service tiers to match your workload requirements. For more information, see service tiers.

Standard Priority Flex Reserved
Green circle with white checkmark icon. Red circle with white X icon indicating error, cancel, or close action. Red circle with white X icon indicating error, cancel, or close action. Red circle with white X icon indicating error, cancel, or close action.

Regional Availability

Regional availability at a glance

Amazon Bedrock offers three inference options: In-Region keeps requests within a single Region for strict compliance, Geo Cross-Region routes across Regions within a geography while respecting data residency, and Global Cross-Region routes worldwide when there are no residency constraints. Refer to the Regional availability by models page for more details.

Region In-Region Geo Global
us-west-2 (Oregon)Green circle with white checkmark icon.Red circle with white X icon indicating error, cancel, or close action.Red circle with white X icon indicating error, cancel, or close action.

Quotas and Limits

The prompt request field accepts 1–5,000 characters. Ray2 also has a maximum model input of 300 tokens, so prompts must satisfy both limits.

Your AWS account has default quotas to maintain the performance of the service and to ensure appropriate usage of Amazon Bedrock. For more information, see Quotas for Amazon Bedrock and the Amazon Bedrock endpoints and quotas.

Sample Code

Step 1 - AWS Account: If you have an AWS account already, skip this step. If you are new to AWS, sign up for an AWS account.

Step 2 - API key: Go to the Amazon Bedrock console and generate a long-term API key.

Step 3 - Get the SDK:

pip install boto3

Step 4 - Set environment variables:

AWS_BEARER_TOKEN_BEDROCK="<provide your Bedrock API key>"

Step 5 - Run your first inference request: This model uses StartAsyncInvoke. Replace the S3 URI with a bucket that you own, and save the file as bedrock-first-request.py.

import boto3

client = boto3.client('bedrock-runtime', region_name='us-west-2')
response = client.start_async_invoke(
    modelId='luma.ray-v2:0',
    modelInput={
        'prompt': 'a whale swimming through space particles',
        'duration': '5s',
        'resolution': '720p',
        'aspect_ratio': '16:9',
        'loop': False
    },
    outputDataConfig={
        's3OutputDataConfig': {
            's3Uri': 's3://your-bucket/output/'
        }
    }
)
print(response['invocationArn'])

For complete request parameters, image-to-video examples, and instructions for checking job status, see Luma AI models.