Use open weight models as your AI coding agent with Amazon Bedrock
Machine Learning Blog
This article demonstrates how to use OpenCode, an open-source terminal-native AI coding agent, with open weight models on Amazon Bedrock for secure and cost-effective AI-assisted development.
- OpenCode runs locally while inference happens securely within AWS accounts with no per-seat fees
- Route different coding tasks to different models: Kimi K3 for reasoning, GPT-OSS 120B for generation, Nemotron 3 Super 120B for throughput
- Multi-model workflows automatically assign optimal models to planning, debugging, and code generation tasks
- Data residency, compliance, and enterprise security controls inherited from Amazon Bedrock infrastructure
- Flex tier pricing offers 50% cost reduction for latency-tolerant batch coding tasks
- Production deployment example: Ethara.AI uses multi-agent orchestration with Oh-My-OpenAgent for specialized AI engineering workflows
OpenCode with Bedrock enables developers to build flexible, secure AI coding assistants that optimize cost and performance by matching models to specific tasks.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
Related articles
Aug 20
2025
2025
Amazon Bedrock now provides simplified access to OpenAI open weight models
Sep 30
2026
2026
Amazon Bedrock Managed Agents, powered by OpenAI, is now available in preview
Sep 18
2026
2026
Migrating multi-model AI agents to Amazon Bedrock AgentCore runtime
Aug 6
2025
2025
OpenAI open weight models now in Amazon Bedrock and Amazon SageMaker JumpStart
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.