Vapi helps developers build, test, and deploy voice agents at scale. We enable everything in between the raw models and production, including telephony, test suites, and real-time analytics.
Hey @Zack Siegel and @Ron , gpt-5 isn’t ready for production because of following reason.
Latency remains uncertain for GPT-5.Multiple deployments need to be set up, and measurements gathered to evaluate performance accurately. (Pending on our end)
Current integration does not include all parameters, such as reasoning effort, requiring adjustments. (Pending on our end)
Prompting techniques will need to be adjusted to work with the different model. Likely not a simple plug-and-play replacement.