Ask HN: Slow OpenAI Inference on AWS Bedrock

1 points by timedude ↗ HN
Inference on AWS Bedrock for OpenAI models has been very slow and glitchy the last few days with today being the worst. Very long latency of over 5 minutes to first token. What's going on?

2 comments

[ 3.5 ms ] story [ 14.0 ms ] thread
us-east-1 seems to be the worst region right now.
likely they sold all the gpu capacity to enterprise clients