Configure Local LLM with OpenCode

Add any OpenAI compatible endpoint to OpenCode

OpenCode doesn’t currently expose a simple “bring your own endpoint” option in its UI. Instead, it ships with a predefined list of cloud providers.

OpenCode fully supports OpenAI-compatible APIs, which means you can plug in any compatible endpoint: including vLLM, LM Studio, Ollama (with a proxy), or your own custom server.

This post shows how to wire up a local vLLM server as a provider, but the same approach works for any OpenAI-compatible endpoint.

---

Prerequisites

• OpenCode installed and working
• A running OpenAI-compatible endpoint (for example: a local vLLM server on http://<host>:8000/v1)

vLLM exposes a /v1 API that matches OpenAI’s Chat Completions API, which makes it an ideal drop-in backend.

---

Step 1 – Register the provider in OpenCode auth

OpenCode stores provider authentication details in:

~/.local/share/opencode/auth.json

If the file does not exist yet, create it.

Add the following entry:

{
  "vllm": {
    "type": "api",
    "key": "sk-local"
  }
}

Notes

• vLLM does not require an API key, but OpenCode expects one to exist.
• Any placeholder value works (sk-local is a common convention).
• If auth.json already exists, merge the vllm block into the existing JSON.

---

Step 2 – Define the OpenAI-compatible provider

Now define the provider itself in:

~/.config/opencode/opencode.json

Create the file if it doesn’t exist.

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "vllm": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "vLLM (local)",
      "options": {
        "baseURL": "http://100.108.174.26:8000/v1"
      },
      "models": {
        "Qwen3-Coder-30B-A3B-Instruct": {
          "name": "My vLLM model"
        }
      }
    }
  },
  "model": "vllm/Qwen3-Coder-30B-A3B-Instruct",
  "small_model": "vllm/Qwen3-Coder-30B-A3B-Instruct"
}

Key fields explained

• @ai-sdk/openai-compatible Tells OpenCode to treat this provider as OpenAI-compatible.
• baseURL Must point to the /v1 endpoint of your server.
• models The key must exactly match the model ID exposed by the backend.
• model / small_model Sets the default model used by OpenCode.

---

Selecting your model

After these steps, restart OpenCode if it’s running.

You can now use:

/model

Your custom provider and model will appear in the selection list.