n8n - 💡(How to fix) Fix Open router model not returning cache and thinking tokens [4 comments, 3 participants]

TL;DR

The issue might be related to the specific configuration of the Open router model node, which only returns limited information in the tokenUsage output.

Guidance

• Verify the configuration of the Open router model node, specifically the x-ai/grok-4.1-fast model, to ensure it is set up correctly.
• Check the documentation for the x-ai/grok-4.1-fast model to see if it has any known limitations or restrictions on the output it provides.
• Test the node with a different model to see if the issue is specific to the x-ai/grok-4.1-fast model.
• Review the node's implementation to ensure it is correctly handling the output from the model.

Notes

The issue may be specific to the x-ai/grok-4.1-fast model or the way it is configured in the Open router model node. Without more information about the node's implementation or the model's documentation, it is difficult to provide a more specific solution.

Recommendation

Apply workaround: Try using a different model or configuration to see if the issue is specific to the current setup, as the x-ai/grok-4.1-fast model may have limitations on its output.