#Which model do GPTs use?
1 messages · Page 1 of 1 (latest)
Hi @supple token. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
OpenAI's GPT (Generative Pretrained Transformers) series uses a variety of models, each with different capabilities and use cases. Here are some of the models mentioned in the provided knowledge sources:
-
GPT base models: These models can understand and generate natural language or code but are not trained with instruction following. They are made to be replacements for the original GPT-3 base models and use the legacy Completions API. Examples include
babbage-002anddavinci-002which are replacements for the GPT-3ada,babbage,curie, anddavincibase models. Source (https://platform.openai.com/docs/models) -
GPT-4o: This is OpenAI's flagship model that can reason across audio, vision, and text in real time. It's available in ChatGPT and the API as a text and vision model. Source (https://help.openai.com/en/articles/7864572-what-is-the-chatgpt-plus-model-selector#h_695f528cfc)
-
GPT-4o mini: This is OpenAI's fastest model, great for everyday tasks. Unlike GPT-4o and GPT-4, tools such as data analysis and file uploads are not available with this model. Source (https://help.openai.com/en/articles/7864572-what-is-the-chatgpt-plus-model-selector#h_695f528cfc)
-
GPT-4: This model is great for tasks that require creativity and advanced reasoning. It also allows you to generate images with DALL•E 3. Source (https://help.openai.com/en/articles/7864572-what-is-the-chatgpt-plus-model-selector#h_695f528cfc)
-
GPT-3.5 (API only): This is a fast model for the simplest routine tasks. Source (https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4-gpt-4-turbo-gpt-4o-and-gpt-4o-mini#h_7faba486a2)
The choice of model depends on your specific use case and requirements. For example, if your use case requires high intelligence or reasoning about images as well as text, gpt-4o and gpt-4-turbo are recommended. If you need the fastest speed and lowest cost, gpt-4o-mini is recommended. Source (https://platform.openai.com/docs/guides/text-generation)