---
title: "Running gh-aw agents on NVIDIA free NIM endpoints"
description: "Wiring GitHub Agentic Workflows to use NVIDIA's free hosted NIM endpoints via Copilot BYOK engine mode"
date: "2026-08-26"

author: "Sameer Khan"
tags: ["AI","Developer Tools","GitHub","NVIDIA"]
category: "Developer Tools"


---

# Running gh-aw agents on NVIDIA free NIM endpoints

Wiring GitHub Agentic Workflows to use NVIDIA's free hosted NIM endpoints via Copilot BYOK engine mode

**Published:** August 26, 2026

**Author:** Sameer Khan
**Category:** Developer Tools
**Reading Time:** 2 min read
**Word Count:** 327

---


I configured GitHub's Agentic Workflows framework (gh-aw) to work with NVIDIA's free hosted NIM endpoints. This post documents the exact configuration and the three failures I hit before getting a successful run.

The task: wire the repo's GitHub Agentic Workflows (github/gh-aw) to NVIDIA's free hosted NIM endpoints (integrate.api.nvidia.com, specifically nvidia/nemotron-3.5-lightning-30b-a3b at 40 RPM free tier) via the Copilot BYOK (Bring Your Own Key) engine mode.

Three failures occurred in sequence before a green run:

1. **AWF proxy rejected every request with 400 'Model has no AI credits pricing'** - This was fixed by adding frontmatter configuration: `models.default-ai-credits-pricing input/output 0.000001` (note that the compiler rejects literal 0, so a tiny value is required)

2. **Proxy token steering silently rewrote the model to claude-sonnet-5** - Resolved by setting `sandbox.agent.token-steering: false` and `model-fallback: false` in the configuration

3. **The agentics sample's timeout-minutes: 15 killed a successful 16.3-minute research session** - Increased timeout to 30 minutes to accommodate longer research sessions

Additional verified facts:

- NVIDIA NIM serves the `/v1/chat/completions` endpoint but returns 404 for `/v1/responses` and `/v1/messages` (verified via curl testing)
- Therefore, the Copilot engine's default completions wire API is the only viable fit
- The threat-detection step requires the larger free model `nvidia/nemotron-3-super-120b-a12b` to emit the strict THREAT_DETECTION_RESULT JSON format
- Sustained sessions can encounter free-tier 403 throttling, which is solved by routing through OpenRouter with NVIDIA BYOK integration (uses NVIDIA quota first, then automatically falls back)
- The primary diagnosis tool is `gh aw audit (run-id)` for inspecting workflow executions

Sources consulted:

- GitHub Agentic Workflows documentation: [https://github.github.com/gh-aw/](https://github.github.com/gh-aw/) (accessed 2026-08-26)
- GitHub next agentics repository: [https://github.com/githubnext/agentics](https://github.com/githubnext/agentics) (accessed 2026-08-26)
- NVIDIA models catalog: [https://build.nvidia.com/models](https://build.nvidia.com/models) (accessed 2026-08-26)

In short: set the tiny credits-pricing value to get past the AWF proxy, disable token steering and model fallback, and raise the session timeout. That's enough to run gh-aw agents on NVIDIA's free models at no cost — including multi-step reasoning tasks and steps like threat detection that require strict JSON output.