---
title: "OpenCode Setup"
description: "Coding models deployed on On-demand Inference can be targeted by open source agentic harnesses like Opencode."
url: https://community.exoscale.com/product/concrete-ai/on-demand-inference/recipes/opencode/
product: "On-Demand Inference"
section: product
last_updated: 2026-10-22
---
> For AI agents: the documentation index is at https://community.exoscale.com/llms.txt. Every page is available as markdown at `<page URL>index.md` or with `Accept: text/markdown`.

# OpenCode Setup

This guide is provided for informational purposes. Because it involves third party tooling we cannot guarantee things still work exactly as described here.

Additional model providers can be added to OpenCode via configuration. This
example assumes that you have access to the private-preview
`nvidia/Qwen3.8-27B-NVFP4` model in `at-vie-2`.

Write the following json to the `~/.config/opencode/opencode.json` file:

```json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "exoscale": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Exoscale",
      "options": {
        "baseURL": "https://inference.at-vie-2.exoscale-cloud.com/v1"
      },
      "models": {
        "qwen": {
          "name": "nvidia/Qwen3.8-27B-NVFP4"
        }
      }
    }
  }
}
```

Adapt as necessary. Once configured:

- run `opencode`
- type `/connect` in the prompt
- select "Exoscale" in the providers list and enter the API key of your
  deployment.
- type `/models` and pick the public model from the list.