Average time until the first token is generated by this model.
Depends on model size, server load, and prompt size.
The average prompt length for this model is -- tokens.
OutputLimittokens
OUTPUT TOKEN LIMITS
Some models limit Response Length for each reply.
This model averages -- output tokens per reply.
Model Status
All costs are given in credits per token.
All usage stats are from the past 10 minutes if possible, otherwise the past 24 hours. Click here to buy credits.