#What is the difference between models?

11 messages · Page 1 of 1 (latest)

tribal night
# 
const response = await openai.createCompletion({
  model: 'text-davinci-003',
  prompt: 'Hello World,
});
cunning granite
#

there is descriptions for each model in the docs

#

including max token amount

tribal night
cunning granite
# tribal night what are max tokens exactly?

The maximum number of tokens to generate in the completion.
The token count of your prompt plus max_tokens cannot exceed the model's context length. Most models have a context length of 2048 tokens (except for the newest models, which support 4096).

its all in the documentation

tepid thunderBOT
#

@tribal night

Image generation is not available in this server.
To start generating images, click here.

tribal night
#

oh okay and is there any limit in openAi requestes? I want to put it in my bot like ask and draw cmd but how many times I can send request to openAI?

#

I just timeouted because of a / 🤦🏻‍♂️

cunning granite
#

free tier rate limit for text & embedding :

•150,000 TPM```