OpenCode

Override OpenCode's OpenAI provider to reach LLMRPM.

Configuration

Setting	Value
API shape	OpenAI-compatible
Base URL	`https://llmrpm.com/api/v1`
Auth	`Authorization: Bearer llmrpm_...`

Place the config in ~/.config/opencode/opencode.json or the project opencode.json.
Override the OpenAI provider baseURL with https://llmrpm.com/api/v1.
Set model to openai/<public-model-id>.
Set small_model to a cheaper/faster model for lightweight work.

Example

opencode.json

{
  "provider": {
    "openai": {
      "options": {
        "baseURL": "https://llmrpm.com/api/v1",
        "apiKey": "llmrpm_YOUR_KEY",
        "timeout": 600000
      }
    }
  },
  "model": "openai/claude-sonnet-5",
  "small_model": "openai/claude-haiku-4.5"
}

Shell

export OPENAI_API_KEY="llmrpm_YOUR_KEY"

opencode auth login
opencode models --refresh

Recommended models

Any public ID from the model list works. Common picks:

claude-sonnet-5— strong model for reasoning, refactors, and coding agents.
claude-haiku-4.5— fast option for autocomplete, small questions, and lightweight tasks.
deepseek-v4-pro— alternative based on your active catalog and plan.

Troubleshooting

Symptom	Cause & fix
Authentication error	Check that the API key has no extra spaces and has not been revoked in the dashboard.
Model rejected	Use a public model ID returned by GET /api/v1/models; do not use display names or aliases.
Connection issue	Confirm the configured base URL is exactly the one shown above and that your network allows HTTPS to llmrpm.com.

Notes

Run opencode auth login if your local setup stores credentials separately.
Run opencode models --refresh if the model list is cached.
Use the openai/ prefix when OpenCode expects a provider/model name.

PreviousContinue Next Amp