Skip to main content
Most coding agents outside Claude Code are easiest to connect to GoModel through the standard OpenAI-compatible API. Flow: OpenCode / Cline / Roo Code / Kilo Code -> GoModel -> your upstream providers

​
Before you start

  • Choose a GoModel master key, for example change-me.
  • Start GoModel with at least one upstream provider key.
  • Use GoModel standard http://localhost:8080/v1 unless your client specifically requires a full endpoint URL.

​
1. Run GoModel

Start GoModel with a master key and at least one upstream provider: 
docker run --rm -p 8080:8080 \
  -e GOMODEL_MASTER_KEY="change-me" \
  -e OPENAI_API_KEY="sk-..." \
  enterpilot/gomodel
You can swap OPENAI_API_KEY for another provider key if that is what your target models use. The important part is that GoModel has at least one upstream provider configured.

​
2. Confirm the OpenAI-compatible API with curl

curl -s http://localhost:8080/v1/chat/completions \
  -H "Authorization: Bearer change-me" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1-mini",
    "messages": [
      {
        "role": "user",
        "content": "Reply with exactly ok"
      }
    ]
  }'
If the gateway is wired correctly, the response will contain ok.

​
3. Configure your coding agent

​
OpenCode

Create an opencode.json file with a GoModel provider: 
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "gomodel": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "GoModel",
      "options": {
        "baseURL": "http://localhost:8080/v1",
        "apiKey": "{env:OPENAI_API_KEY}"
      },
      "models": {
        "gpt-4.1-mini": {
          "name": "GPT-4.1 Mini",
          "limit": {
            "context": 200000,
            "output": 32768
          }
        }
      }
    }
  }
}
Then export the GoModel key: 
export OPENAI_API_KEY=change-me

​
Cline

In Cline, choose:
  • API Provider: OpenAI Compatible
  • Base URL: http://localhost:8080/v1
  • API Key: change-me
  • Model ID: a model returned by GET /v1/models

​
Roo Code

In Roo Code, choose:
  • API Provider: OpenAI Compatible
  • Base URL: http://localhost:8080/v1
  • API Key: change-me
  • Model ID: a model returned by GET /v1/models
Roo Code requires native tool calling. Choose a model and provider path that support OpenAI-compatible tool calling.

​
Kilo Code

In Kilo Code, choose:
  • API Provider: OpenAI Compatible
  • Base URL: http://localhost:8080/v1
  • API Key: change-me
  • Model ID: a model returned by GET /v1/models
Kilo Code also supports a full endpoint URL if you need it: 
http://localhost:8080/v1/chat/completions
Start with the simpler base URL first and only switch to a full endpoint URL if your setup requires it.

​
4. Run a test prompt

For OpenCode, this validated command worked: 
opencode run -m gomodel/gpt-4.1-mini \
  'Reply with exactly ok and no punctuation.'
The validated result was: 
ok
For Cline, Roo Code, and Kilo Code, save the provider settings above and send a small prompt such as: 
Reply with exactly ok and no punctuation.

​
5. Check the traffic in GoModel

Open the GoModel dashboard audit logs: http://localhost:8080/admin/dashboard/audit This is the quickest way to confirm that your coding agent is reaching GoModel and to inspect each interaction. From the same dashboard, you can keep following your GoModel traffic and usage.

​
Current status

  • OpenCode was validated locally and worked against standard http://localhost:8080/v1
  • Cline, Roo Code, and Kilo Code follow the same OpenAI-compatible setup model
  • Roo Code needs native tool calling support from the selected model
  • Kilo Code can use either a base URL or a full endpoint URL

​
References

​
Validated on March 10, 2026

This guide combines:
  • local validation against a GoModel instance on http://localhost:8080
  • local validation with OpenCode 1.1.36
  • official documentation for Cline, Roo Code, and Kilo Code
Local validation confirmed:
  • OpenCode worked against http://localhost:8080/v1
  • the validated OpenCode request used POST /v1/chat/completions
  • GoModel dashboard audit logs showed the OpenCode traffic immediately