# AWS Publishes Guide to Running OpenCode Coding Agent on Bedrock Open Weight Models

> The AWS Machine Learning Blog outlined pairing the open-source OpenCode terminal agent with open weight models on Amazon Bedrock, claiming data stays in the customer's AWS account with no per-seat fees. It cites Kimi K3, GPT-OSS 120B and

- **Topic**: Models
- **Published**: 2026-09-23T23:07:38.420Z
- **Canonical URL**: https://highsignal.sh/stories/aws-publishes-guide-to-running-opencode-coding-agent-on-bedrock-open-weight-mode-c20b62dd

## Why It Matters

The post pitches a private, pay-per-use path for coding agents as an alternative to third-party APIs and per-seat tools, and notes claims of open weight performance parity with proprietary models. It also describes cross-Region routing and pricing mechanics for one model.

## Key Findings & Analysis

### What AWS described

AWS's post presents OpenCode as a terminal-native, open-source coding agent written in Go that reads and edits files, runs shell commands and uses LSP diagnostics, connecting to 75-plus LLM providers. It proposes running it with open weight models on Bedrock so inference stays inside the AWS account, switching models as a single API parameter change. The post names Kimi K3, OpenAI GPT-OSS 120B and NVIDIA Nemotron 3 Super 120B as examples and says it will walk through setup and multi-model workflows.

### Routing and cost claims

For regional control, the post says Kimi K3 can be invoked via a cross-Region inference profile, with a global profile routing requests to any supported commercial AWS Region and costing roughly 10 percent less than a geographic profile; a US profile keeps processing within the US geography. AWS says models accessed through an in-Region or geographic profile run in that Region or geography.

### Vendor-cited performance, as claimed

The post cites a CrowdStrike fine-tune of NVIDIA Nemotron reaching 96 percent valid query accuracy, versus 61 percent for GPT-4o and 94 percent for Claude Sonnet 4.5, as an example of domain-specific open weight performance. These are figures AWS attributes to CrowdStrike, not independent AWS benchmarking. AWS also cites a McKinsey 2025 report that 76 percent of organizations expect to increase open source AI usage.

### Deployment and incentives

AWS says Ethara.AI already runs this architecture in production with multi-agent orchestration. It argues token consumption in agentic workflows makes cost-per-token critical, and that open weights allow fine-tuning and domain adaptation so smaller models can replace pricier general-purpose ones.

## Original Evidence & Verbatim Citations

> "Use open weight models as your AI coding agent with Amazon Bedrock"

— *Grounded field: headline*

> "OpenCode is an open source, terminal-native AI coding agent built in Go."

— *Grounded field: headline*

> "When you pair OpenCode with open weight models on Bedrock, you get a coding assistant that runs locally while inference happens securely within your AWS account. There’s no infrastructure to manage and no per-seat fees."

— *Grounded field: summary*

> "walk through practical coding examples using Moonshot AI Kimi K3, OpenAI GPT-OSS 120B, and NVIDIA Nemotron 3 Super 120B"

— *Grounded field: summary*

> "But most options require you to send your proprietary data to a third-party API, lock you into a single model provider, or charge per-seat subscriptions regardless of how much you use them."

— *Grounded field: whyItMatters*

> "Global cross-Region inference costs approximately 10% less than a geographic profile."

— *Grounded field: whyItMatters*

> "It reads and edits files, runs shell commands, and understands project structure through Language Server Protocol (LSP) diagnostics. It connects to over 75 large language model (LLM) providers including Amazon Bedrock."

— *Grounded field: section:0*

> "Switching models is a single API parameter change on Amazon Bedrock."

— *Grounded field: section:0*

> "You can invoke Kimi K3 through a cross-Region inference profile. For workloads without regional restrictions, we recommend using the global profile, global.moonshotai.kimi-k3, which routes each request to any supported commercial AWS Region worldwide."

— *Grounded field: section:1*

> "The US geographic profile, us.moonshotai.kimi-k3, keeps processing within the US geography for data residency requirements."

— *Grounded field: section:1*

> "CrowdStrike’s fine-tuned NVIDIA Nemotron achieved 96% valid query accuracy, outperforming GPT-4o (61%) and Claude Sonnet 4.5 (94%)."

— *Grounded field: section:2*

> "According to McKinsey’s Open-source technology in the age of AI report (2025), 76 percent of organizations expect to increase open source AI usage"

— *Grounded field: section:2*

> "We also share how Ethara.AI deploys this architecture in production with multi-agent orchestration to power AI engineering and research workflows at scale."

— *Grounded field: section:3*

> "Customization and control: Open weights support fine-tuning, distillation, and domain adaptation. Smaller models can replace expensive general-purpose ones while maintaining quality."

— *Grounded field: section:3*

## Primary Sources & Citations

- [Use open weight models as your AI coding agent with Amazon Bedrock](https://aws.amazon.com/blogs/machine-learning/use-open-weight-models-as-your-ai-coding-agent-with-amazon-bedrock/) — *AWS Machine Learning Blog* (Primary source)

---

[← Back to front page](https://highsignal.sh/) | [Daily Brief](https://highsignal.sh/brief) | [All stories](https://highsignal.sh/latest)