I’m actually curious how long could gpt output be?
Like if I ask it to translate a whole book would it work?
#output length
slender lily
covert galeBOT
Hi @slender lily. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
The length of the output from a GPT model is primarily controlled by the max_tokens parameter. However, the total maximum length also depends on the specific model used for the request. For instance, the GPT-3.5 model has a maximum context length of 16,385 tokens, while the GPT-4o and GPT-4o mini models have a context length of 128k tokens, which is roughly equivalent to an average to longer novel.
However, it's important to note that translating a whole book in one go might not be feasible due to these token limitations. Also, the model's performance might degrade with very long inputs. It's generally more effective to break down the task into smaller chunks.
You can also influence the length of the model's response by providing instructions to generate the desired output length, such as a specific number of items in a list, or by using stop sequences. However, there is currently no way to set a minimum number of tokens.
Sources:
- Controlling the length of OpenAI model responses (https://help.openai.com/en/articles/5072518-controlling-the-length-of-openai-model-responses)
- Which model should I use? (https://help.openai.com/en/articles/7102672-how-can-i-access-gpt-4-gpt-4-turbo-gpt-4o-and-gpt-4o-mini#h_7faba486a2)