Is there an expectation or road map that will see the ChatGPT engine (for want of a better word ) available for installation on a client’s own infrastructure? For private secure use.
What are the challenges that would have to be overcome?
The following is a section taken from Introducing ChatGPT and Whisper APIs
briefly describing what I think would be similar to your requirements, a link to the sales enquiry page is included at the bottom.
"Dedicated instances
We are also now offering dedicated instances for users who want deeper control over the specific model version and system performance. By default, requests are run on compute infrastructure shared with other users, who pay per request. Our API runs on Azure, and with dedicated instances, developers will pay by time period for an allocation of compute infrastructure that’s reserved for serving their requests.
Developers get full control over the instance’s load (higher load improves throughput but makes each request slower), the option to enable features such as longer context limits, and the ability to pin the model snapshot.
Dedicated instances can make economic sense for developers running beyond ~450M tokens per day. Additionally, it enables directly optimizing a developer’s workload against hardware performance, which can dramatically reduce costs relative to shared infrastructure. For dedicated instance inquiries, [contact us]"
1 Like
Thank you.
I need to have 25 characters to submit a response.
1 Like
Hello,
I hope this message finds you well.
We submitted a request for a dedicated instance through the “contact sales” link you’ve attached, but haven’t received any updates yet. Can you please provide us with any information about that or approval timeline? Also, could you provide information on how to contact the support team or a human team member for the update on the status of dedicated instance request as I couldn’t find any option to do so.
Looking forward to your response.
Thank you
Hi,
Not sure what might have happened to the sales enquiry, might be worth resubmitting it, in case of a technical glitch.
You can use the chat bot in the bottom right corner (pen icon) on the help site over at https://help.openai.com to contact support.
1 Like
Thank you for your prompt response. I appreciate your help with resubmitting the request. However, I have already tried using the support chatbot and unfortunately it keeps replying that it could not find the answer to my question. Is there any other way to get in touch with the support team to get assistance with my request? I would appreciate any further guidance or assistance you can provide. Thank you.
I only know of the sales contact page, I don’t work for OpenAI, so I’m not able to expedite anything for you I’m afraid. Perhaps making a new post here enquiring about contacting sales may attract some attention, not sure if already answered threads like this one get to be very visible.
Alright, thank you for your response!