Amazon Bedrock enables open weight models for OpenCode AI coding agent
OpenCode is an open‑source, terminal‑native AI coding agent written in Go that can read, edit, and run code while understanding project structure via LSP diagnostics. The tool connects to more than 75 large language model providers, including Amazon Bedrock, allowing developers to run a coding assistant that stays inside their AWS account and incurs only pay‑per‑use charges.
Key points
- OpenCode links to 75+ LLM providers and runs on Amazon Bedrock’s managed, serverless endpoints.
- Developers can switch between Kimi K3, GPT‑OSS 120B, and Nemotron 3 Super 120B per task via a single API parameter.
- Bedrock’s Flex tier offers 50 % lower per‑token cost; data stays in‑account and complies with major security standards.
The post shows how to configure OpenCode with Bedrock’s open‑weight models such as Moonshot AI’s Kimi K3, OpenAI’s GPT‑OSS 120B, and NVIDIA’s Nemotron 3 Super 120B. It highlights benefits like data residency, compliance with HIPAA, SOC 2, ISO 27001, FedRAMP and GDPR, and flexible pricing tiers (Priority, Standard, Flex) that can cut costs by up to 50 %. The article cites McKinsey’s 2025 report that 76 % of organizations plan to increase open‑source AI usage, and CrowdStrike’s claim that a fine‑tuned Nemotron achieved 96 % valid query accuracy, outperforming GPT‑4o (61 %) and Claude Sonnet 4.5 (94 %).
Ethara.AI’s production deployment is described, where OpenCode and an orchestration layer route tasks to the most suitable model, demonstrating how enterprises can build scalable, secure AI‑assisted development pipelines on Bedrock.
Model page: Kimi K3 →
The story so far
3 episodes →- Amazon Bedrock enables open weight models for OpenCode AI coding agentthis story
Use open weight models as your AI coding agent with Amazon Bedrock
AWS Machine Learning Blog · 23 September 2026
Loading the full article…
This text was published by AWS Machine Learning Blog and written by Aris Tsakpinis. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- OpenAI adds GPT-Live voice to ChatGPT app for hands‑free task delegation · 5 src
- Amazon blocks Meta's Muse AI agent from shopping on its platform · 22 src
- YouTube says it will let users build custom feeds using Gemini AI · 4 src
- Meta tests Muse calls that are actually made by humans in a call center · 5 src
- Meta's Muse AI agent tops US App Store, outpaces ChatGPT downloads; zero-day flaw reported · 23 src
Comments
via GitHub Discussions