#GPT 4 mini and Fine-tuning model for assistant API

1 messages · Page 1 of 1 (latest)

fervent shore
#

can we use GPT 4 mini and Fine-tuned model for assistant API

vagrant kiteBOT
#

Hi @fervent shore. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

Yes, you can use GPT-4o mini with the Assistant API. GPT-4o and GPT-4o mini are available to anyone with an OpenAI API account, and you can use the models in the Chat Completions API (https://platform.openai.com/docs/guides/text-generation/chat-completions-api), Assistants API (https://platform.openai.com/docs/api-reference/assistants), and Batch API (https://platform.openai.com/docs/guides/batch) (source (https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4-gpt-4-turbo-gpt-4o-and-gpt-4o-mini#h_9bddcd317c)).

As for fine-tuned models, you can use them with the Assistants API as well. However, as of the latest update, only fine-tuned versions of gpt-3.5-turbo-0125 are supported (source (https://platform.openai.com/docs/assistants/whats-new)).

Please note that the Assistants API does not support the use of fine-tuned models in general (source (https://community.openai.com/t/640916)). So, if you're planning to use a fine-tuned model other than gpt-3.5-turbo-0125, it might not be supported.

For the most accurate and up-to-date information, I recommend checking the official OpenAI documentation or reaching out to OpenAI support.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: