Broccolini
10/21/2025, 7:07 AMVapi Support Bot
10/21/2025, 7:09 AMsummaryPlan. To ensure your assistant's LLM (Grok4Reasoning) is used, double-check your transfer configuration and make sure your summaryPlan does not specify a separate model. Here’s an example of a correct configuration:
json
"transferPlan": {
"mode": "warm-transfer-with-summary",
"summaryPlan": {
"enabled": true,
"messages": [
{ "role": "system", "content": "Please provide a summary of the call." },
{ "role": "user", "content": "Here is the transcript:\n\n{{transcript}}\n\n" }
]
// No "model" property here
}
}
If the issue persists, contact Vapi support with your call ID, as this may be a platform-level bug.
[See documentation](https://docs.vapi.ai/call-forwarding)
Source:
- [Call Forwarding](https://docs.vapi.ai/call-forwarding)Broccolini
10/21/2025, 7:13 AMChiranjeet Mishra
10/22/2025, 11:28 PM