I’m looking to deploy a model that can ingest anywhere between 2000 and 70000 tokens as the input and an output of anywhere between 1000 and 10000 tokens. This is my first deployment and foray into OpenAI and it looks like GPT-4-1106-preview would be the best fit for this use case but isn’t yet ready for production. This model will be deployed on Bubble as a prototype. I’m located in California and wondering what my best options are for region and model type for this kind of build?
Related Topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Understanding which GPT model is ready for production | 0 | 1411 | January 26, 2024 | |
| I want to use GPT 4 with 128k, how do I do it? | 1 | 238 | June 7, 2024 | |
| Trying to understand why I'm hitting token limit with API | 8 | 3057 | February 27, 2024 | |
| Create or customize models with more tokens | 3 | 654 | November 29, 2023 | |
| Can we use GPT 4-preview (Turbo) in production? | 4 | 3049 | January 30, 2024 |