Number of requests per second
Hello! Can you clarify about the number of requests per second?
Here (https://docs.runpod.io/serverless/references/operations) you write about "Rate limit: 2000 per second"
But here(https://docs.runpod.io/serverless/endpoints/invoke-jobs) Rate Limits "/runsync: 2000 requests every 10 seconds."
Endpoint operations | RunPod Documentation
Comprehensive guide on interacting with models using RunPod's API Endpoints without managing the pods yourself.
Invoke a Job | RunPod Documentation
Run Endpoints in RunPod.
5 Replies
Oh wow, nice find. @flash-singh can you confirm?
its per 10 seconds 2k rewuests
And can we extend this quantity?
We need about 1250 requests per second
Does @PatrickR need to fix the doc thats incorrect?
what kind of requests are these? llm? text to image? you can pm me details, we can talk further