Validate these three API requirements first
- Base URL is exactly https://monkeytheme.com/v1
- API key is complete
- Model name is the real name sold in the panel
curl https://monkeytheme.com/v1/models -H "Authorization: Bearer sk-your-key"
curl https://monkeytheme.com/v1/chat/completions -H "Authorization: Bearer sk-your-key" -H "Content-Type: application/json" -d '{
"model": "gpt-4.1-mini",
"messages": [{"role": "user", "content": "Reply with OK only."}],
"max_tokens": 12,
"temperature": 0
}'Recommended Hermes workflow
For Hermes, switch config only after curl succeeds.
hermes config set model.base_url https://monkeytheme.com/v1 hermes config set model.api_key sk-your-key hermes config set model.default gpt-4.1-mini # then restart gateway or open a new session
Recommended OpenClaw workflow
OpenClaw has the same core dependency.
Common mistakes
- No restart or fresh session after config changes.
- 401 caused by incomplete key or old env value.
- Double /v1 path.
- Model nickname instead of real name.