"config validation failed: models.providers.ollama.baseURL"
This validation error means the baseUrl in your Ollama provider config is missing or malformed. It must be a complete URL with scheme and host, and it must not end in /v1, since the /v1 path drops tool calls under streaming. Open openclaw.json, set baseUrl to the native http://127.0.0.1:11434, save, and restart the gateway.
Likely cause
The baseUrl for your Ollama provider is missing or malformed. It must be a complete URL with the scheme and host, and it must NOT end in /v1 (the /v1 path drops tool calls).
The fix
- 1 Open your openclaw.json.
- 2 Set baseUrl to the native Ollama URL with no /v1 suffix.
- 3 Save and restart the gateway.
"baseUrl": "http://127.0.0.1:11434"Hit a different error?
Paste any agent error and get the cause and fix in seconds.
Frequently asked questions
Does this mean my Ollama install is broken?
No. This is purely a config-file format error in openclaw.json. Your Ollama server and pulled models are fine, the provider URL just needs the right value.
Why can't I use the /v1 endpoint in baseUrl?
The native /api/chat path preserves tool calls under streaming, but the /v1 OpenAI-compat path drops them. Always omit the /v1 suffix for OpenClaw's Ollama provider.
How do I confirm the fix worked?
Save openclaw.json and start the gateway. If it starts without a validation error, the config is valid. Run openclaw doctor --deep to verify provider connectivity end to end.
Stop firefighting agent errors
Decoding errors one at a time is the manual version of what BetterClaw automates. Run your OpenClaw agents hosted with managed models, retries and config validation built in.
$19/month per agent · BYOK · 7-day money-back guarantee