Hello, as we all know, GPT 5 has been pretty bad for vapi, but how are the two new 5.1 models? Are they any good? I'm also curious to know if the latency times are correct, 5.1 instant is just as fast as plain 5.1. It also has the exact same specs. Any noticable difference there?

GPT-5.1 is overall better than 4.1 because it gives more accurate, detailed, and consistent responses, and it handles conversations more naturally. For Vapi users, the main difference is quality vs. speed: GPT-5.1 gives the best response quality, while GPT-5.1-Instant is almost as fast as 4.1 but still noticeably smarter. If your latency is the same for both, then using plain 5.1 will give you the best results, and Instant is a good option when you need faster replies with only a small drop in detail.

Hi Operations, You can now utilize new GPT-4.1 models, such as

gpt-4.1

,

gpt-4.1-mini

, and

gpt-4.1-nano

. These models are available through the [OpenAI API and Azure OpenAI](https://docs.vapi.ai/changelog/2025/5/15). If you're working within Azure OpenAI, you can configure models like

gpt-4.1-2025-04-14

,

gpt-4.1-mini-2025-04-14

, and

gpt-4.1-nano-2025-04-14

via the API, with console configuration coming soon. For any of these configurations, please ensure you're referring to the corresponding [API documentation](https://docs.vapi.ai/api-reference/assistants/update). If you have further needs or questions about these model versions or their capabilities, just let me know.