Listing Thumbnail

    OpenAI GPT-5.6 Luna (Amazon Bedrock Edition)

     Info
    Sold by: OpenAI 
    Deployed on AWS
    AWS Free Tier
    OpenAI GPT-5.6 Luna brings a fast, cost-efficient GPT-5.6 model for everyday AI workflows and scalable applications to Amazon Bedrock.
    4
    These options are for OpenAI GPT-5.6 Luna (Amazon Bedrock Edition).
    View 2 other options

    Overview

    OpenAI GPT-5.6 Luna is the fastest and most cost-efficient model in the GPT-5.6 family. It is designed for teams building everyday AI workloads where responsiveness, scale, and practical performance matter. Luna is well suited for workflow automation, content and knowledge tasks, lightweight coding assistance, and other common use cases that benefit from fast, dependable model performance. It gives developers a practical way to bring GPT-5.6 capabilities into production workloads that need to run efficiently. Through Amazon Bedrock, organizations can use GPT-5.6 Luna in the AWS environment where many enterprise applications and operational workflows already run. Teams can access OpenAI model capabilities alongside their existing AWS security, governance, procurement, billing, and operational workflows.

    Highlights

    • A fast, cost-efficient GPT-5.6 model for everyday AI workflows and applications where responsiveness and efficiency matter
    • Designed for teams that need strong capability while optimizing for speed, scale, and cost.
    • Available through Amazon Bedrock so customers can deploy OpenAI model capabilities within their existing AWS environment.

    Details

    Sold by

    Delivery method

    Deployed on AWS

    Features and programs

    Financing for AWS Marketplace purchases

    AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
    Financing for AWS Marketplace purchases

    Pricing

    OpenAI GPT-5.6 Luna (Amazon Bedrock Edition)

     Info
    Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
    Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator  to estimate your infrastructure costs.

    Usage costs (84)

     Info
    Dimension
    Cost/unit
    cached_input_tokens_batch
    $0.055
    input_tokens_long_ctx_standard
    $0.44
    input_tokens_long_ctx_flex
    $0.22
    input_tokens_long_ctx_batch
    $0.22
    output_tokens_long_ctx_standard
    $1.98
    output_tokens_long_ctx_flex
    $0.99
    output_tokens_long_ctx_batch
    $0.99
    cached_input_tokens_long_ctx_standard
    $0.22
    cached_input_tokens_long_ctx_flex
    $0.11
    cached_input_tokens_long_ctx_batch
    $0.11

    AI Insights

     Info

    Dimensions summary

    You pay per token, with no upfront commitment. Charges split into input tokens, output tokens, and cache-related tokens (cached input, cache writes, and cache reads). Each of these applies across processing modes: standard, priority, flex, and batch. You also choose a context scope, either regular or long-context, and a deployment scope, either regional or global. A separate set of cache-write dimensions covers a 30-minute retention window. This structure lets you match each request to a speed, context length, and cost combination, so pricing scales with how you route work.

    Top-of-mind questions for buyers

    Each unit is one token processed by the model. Input tokens cover text you send. Output tokens cover text the model generates. Cache-related tokens count tokens read from or written to a reuse cache. You are billed per token consumed in each category.
    Standard is the default speed. Priority processing runs faster requests. Flex processing favors lower-cost, less time-sensitive work. Batch processing handles grouped requests. Each mode has its own per-token rate across input, output, and cache dimensions, so your route choice sets the price.
    Output tokens and input tokens both meter independently and appear together on your invoice. Output tokens often cost more per token than input. Cache reads reduce repeated input costs when prompts reuse content. Cache writes add a charge to store that content, with a 30-minute retention option.
    openai.com
    Helpful?

    Vendor refund policy

    All sales are final. Fees are non-refundable.

    How can we make this page better?

    Tell us how we can improve this page, or report an issue with this product.
    Tell us how we can improve this page, or report an issue with this product.

    Compliance

    Compliance profile

    This information is produced by a third-party provider from the provider's trust center data and is provided for informational purposes only.
    FedRAMP 20x
    FedRAMP 20x
    SOC 2 Type 2
    SOC 2 Type 2
    PCI DSS v4.0.1
    PCI DSS v4.0.1
    GDPR
    GDPR
    ISO/IEC 27001:2022
    ISO/IEC 27001:2022
    CCPA
    CCPA
    CSA STAR
    CSA STAR
    ISO/IEC 27017:2015
    ISO/IEC 27017:2015
    ISO/IEC 27018:2019
    ISO/IEC 27018:2019
    ISO/IEC 27701:2019
    ISO/IEC 27701:2019
    ISO/IEC 42001:2023
    ISO/IEC 42001:2023
    SOC 3
    SOC 3

    Legal

    Vendor terms and conditions

    Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .

    Content disclaimer

    Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.

    Usage information

     Info

    Delivery details

    Software as a Service (SaaS)

    SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.

    Support

    Vendor support

    For support, visit

    AWS infrastructure support

    AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.

    Similar products

    Customer reviews

    Ratings and reviews

     Info
    4
    1 ratings
    5 star
    4 star
    3 star
    2 star
    1 star
    0%
    100%
    0%
    0%
    0%
    1 AWS reviews
    reviewer2921490

    Classification has reduced costs but still needs better OCR accuracy and image handling

    Reviewed on Nov 03, 2026
    Review from a verified AWS customer

    What is our primary use case?

    The solution is used for classification.

    How has it helped my organization?

    The solution provides cost savings.

    What is most valuable?

    One of the most valuable features is inference.

    What needs improvement?

    There is room for improvement in the accuracy of OCR, and there is a bug with images from earlier turns leaking into the later turns.

    For how long have I used the solution?

    I have used the solution for 1 month.

    What's my experience with pricing, setup cost, and licensing?

    The setup cost was great.

    Which other solutions did I evaluate?

    I considered alternate solutions such as Haiku 5.5 and GPT-OSS.

    What other advice do I have?

    Getting a marketplace subscription was extremely painful. It took several weeks, failed support calls, and confusion in AWS caused by October 4 changes in the subscription process in AWS. It was a very bad experience and a lot of money was wasted on an older model.

    View all reviews