absent-sapphire•6mo ago
Why model change to gpt-4o-mini when speaking ?
Hi i use chatgpt-4o-latest model on asistan. Now i added an tool and speaking is changed. I see on logs model is changed to gpt4o-mini. Why ? Also i catched a WARN its says tools is not supported in this model. Is can be reason ? But i think chatgpt-4o-latest support tool or or am I wrong. ?
11:10:22:126
[LOG]
Model request started (attempt #1, chatgpt-4o-latest, openai)
11:10:22:266
[LOG]
Model request started (attempt #2, gpt-4o-mini-2024-07-18, openai)
11:10:22:266
[WARN]
Model request failed (attempt #1, reason: (tools is not supported in this model. For a list of supported models, refer to https://platform.openai.com/docs/guides/function-calling#models-supporting-function-calling.))
5 Replies
It appears that the
Check your assistant's model configuration and ensure you are using a model that explicitly supports tool/function calling. You can refer to the OpenAI documentation on function calling support for the latest compatibility list. Sources: - Vapi Changelog February 25, 2025 - Vapi OpenAI Model Documentation
chatgpt-4o-latest model does not support tools/function calling in your current setup, which triggers a fallback to gpt-4o-mini. The warning in your logs—"tools is not supported in this model"—is likely the reason for the model switch.
Actionable step:Check your assistant's model configuration and ensure you are using a model that explicitly supports tool/function calling. You can refer to the OpenAI documentation on function calling support for the latest compatibility list. Sources: - Vapi Changelog February 25, 2025 - Vapi OpenAI Model Documentation
⤵️ Mention @Vapi Support Bot for follow-ups 🐥
absent-sapphireOP•6mo ago
thanks
fair-rose•6mo ago
checking if this is resolved/solved for you?
absent-sapphireOP•6mo ago
yes thanks
fair-rose•6mo ago
You're welcome