GuidesOpenClaw
Troubleshoot OpenClaw + ORGN Gateway
Fix OpenClaw provider configuration, authentication, and model routing issues with ORGN Gateway.
Provider not recognized
Verify providers.ollm exists in openclaw.json and JSON is valid:
cat ~/.openclaw/openclaw.json | jq .Environment variable not detected
No API key found for provider 'ollm'echo $OLLM_API_KEYReload shell and restart OpenClaw after exporting.
Authentication (401 / 403)
baseUrl:https://api.gateway.orgn.com/v1- Key valid in Gateway console
- Auth profile:
openclaw auth listand"apiKey": "auth:ollm:default"
Model not found
Use underscore Gateway IDs:
| Wrong | Correct |
|---|---|
near/GLM-4.6 | near_glm_4_7 |
ollm/near/GLM-4.6 | ollm/near_glm_4_7 |
Model must appear in models.providers.ollm.models and agent primary must use ollm/<id>.
Agent starts but does not respond
Check logs, confirm primary model is set, restart gateway:
openclaw gateway restartRate limits
Monitor usage in the Gateway console.
Checklist
- Valid JSON in
openclaw.json -
baseUrlcorrect -
OLLM_API_KEYor auth profile configured - Underscore model IDs
- Gateway console shows incoming requests
Use OpenClaw with ORGN Gateway
Configure OpenClaw to route agent requests through ORGN Gateway's OpenAI-compatible API — TEE or ZDR models per your selection.
Integrate ORGN Gateway with the OpenAI SDK
Configure the OpenAI SDK to route inference through ORGN Gateway — swap base URL, API key, and model IDs.