AWS Transform adds generative AI model migration assessment
AWS Transform now supports model-to-model migration assessment for generative AI workloads, producing a plan to move from third-party providers to Amazon Bedrock. This AI-powered agent scans code, identifies models, gathers requirements, and maps them to Bedrock equivalents with cost comparisons and code changes. The feature helps consolidate AI workloads on AWS, offering enhanced security and tooling, and is available in all AWS Transform regions at no extra charge.
- →Generative AI model-to-model migration assessment
- →Support for diverse migration sources and architectures
- →Intelligent cost optimization and model lifecycle awareness
- →Zero-code-change migration path option
- →Availability and prerequisites
Features (1) ›
- Generative AI model-to-model migration assessment
AWS Transform now offers a custom transformation that assesses generative AI workloads and provides a migration plan to Amazon Bedrock. It scans code, identifies AI SDKs and models, and maps them to Bedrock equivalents with cost comparisons and code changes.
Enhancements (3) ›
- Support for diverse migration sources and architectures
The transformation supports migrations from OpenAI, Google Gemini, Anthropic SDK, and open-source models via LiteLLM or Ollama. It handles direct SDK integrations, framework patterns like LangChain and LlamaIndex, agentic architectures, and multi-provider routing layers.
- Intelligent cost optimization and model lifecycle awareness
The agent includes recommendations for tiered model routing and prompt caching analysis. It also incorporates model lifecycle awareness, excluding models within 90 days of their end-of-life from recommendations.
- Zero-code-change migration path option
For certain workloads, the transformation recommends Amazon Bedrock's OpenAI-compatible endpoints as a zero-code-change migration path.
Notes (1) ›
- Availability and prerequisites
AWS Transform model-to-model migration is available in all AWS Regions where AWS Transform is offered at no additional charge. To get started, users need to install the ATX CLI and run the mke-genai-model-migration custom transformation.
https://aws.amazon.com/about-aws/whats-new/2026/06/aws-transform-model-to-model-assessments