1. Group models by protocol
openai-responsesfor models advertising/responses.openai-completionsfor Chat Completions models.anthropic-messagesfor models advertising/v1/messages.
2. Provider example
JSON fragment
{
"models": {
"mode": "merge",
"providers": {
"ghc-responses": {
"baseUrl": "http://127.0.0.1:8313/v1",
"apiKey": "1",
"api": "openai-responses",
"models": [{
"id": "YOUR_RESPONSES_MODEL_ID",
"reasoning": true,
"input": ["text", "image"],
"contextWindow": 128000,
"maxTokens": 16384,
"cost": {"input": 0, "output": 0, "cacheRead": 0, "cacheWrite": 0}
}]
}
}
}
}Inside containers, 127.0.0.1 points to the OpenClaw container. Use the ghc-api service name or another reachable host address.
3. Use accurate capabilities
Populate context, output, image input, and reasoning fields from live metadata. Cost fields are client-side estimates; use zero rather than inventing precision.
Base URL depends on the adapter.
OpenAI-compatible providers generally use /v1; Anthropic Messages generally uses the service root.
4. Troubleshoot
- Test network reachability from the OpenClaw process or container.
- Match API type, endpoint, and model.
- Use an approved token when authentication is enabled.
- Inspect the actual request path in ghc-api.
Next step
Inspect the models and endpoints available to your account before copying a model ID into client configuration.
Inspect models and parameters →