News for hackers. Stuff that matters.

A comment on Gemini CLI. Parent comment

Re:Gemini CLI by nikcub on Wednesday June 25, 2025 @04:09PM (#44381368)
The key to running LLM services in prod is setting up Gemini in Vertex, Anthropic models on AWS Bedrock and OpenAI models on Azure. It's a completely different world in terms of uptime, latency and output performance.
[ Parent | on HN ]
Re:Gemini CLI by shpat on Wednesday June 25, 2025 @08:32PM (#44383127)
Have you had any luck getting your Claude quota bumped on Bedrock? I tried working through AWS support but got nowhere. Gave up and used Vertex + Gemini
[ Parent | on HN ]
Re:Gemini CLI by com2kid on Thursday June 26, 2025 @02:18AM (#44384669)
Does OpenAI on azure still have that insane latency for content filtering? Last time I checked it added a huge # to time to first token, making azure hosting for real time scenarios impractical.
[ Parent | on HN ]
Re:Gemini CLI by shakna on Thursday June 26, 2025 @06:11AM (#44385890)
Yes.

Unless you convince MS to let you at the "Provisioned Throughput" model. Which also requires being big enough for sales to listen to you.

[ Parent | on HN ]