Chat Completion
Last updated
Last updated
: Required (JWT token or Api Key)
Generates a chat completion response using the specified model. Requires sufficient user credits and valid model.
ID of the model to use for completion
A list of messages comprising the conversation so far
Whether to stream back partial progress
false
What sampling temperature to use, between 0 and 2
1
An alternative to sampling with temperature, called nucleus sampling
1
The maximum number of tokens to generate in the completion
Seed for deterministic results
Maximum number of completion tokens
Number between -2.0 and 2.0 to penalize repeated tokens
0
Number between -2.0 and 2.0 to penalize tokens already present in the text
0