Tech

Is "GPU-hour per user" a sane way to price LLM inference?

Hacker News (Newest) By mirastacklabs Nov 7, 2026 · 10:15 PM 0 views 0 comments

Article URL: https://www.mirastacklabs.ai/

Comments URL: https://news.ycombinator.com/item?id=50410369

Points: 1

# Comments: 0

Hacker News (Newest) Original story · www.mirastacklabs.ai

Read the full story

How does this story make you feel?

👍 ❤️ 💡 😮 😂 😢 😠

Discussion (0)

No comments yet. Start the conversation!

Hacker News (Newest) + Follow

Section: Tech + Follow

Up next from Hacker News (Newest)

Kirlian Photography: Building Your Own Equipment

Article URL: https://imagesco.com/articles/kirlian/kirlian-photography.html Comments URL: https://news.ycombinator.com/item?id=50410359 Points: 3 # Comments: 0

Hacker News (Newest) 5 hours ago

Show HN: Golang DL/ML primitives with inference, diffusion, vision, systemone

Hacker News (Newest) Oct 14, 2026

Tech

Ask HN: If LLM reverse engineering is deemed illegal, is that precedent for OSS?

Hacker News (Newest) 8 hours ago

Tech

llm-d v1.0: State-of-the-art inference

Hacker News (Newest) Oct 20, 2026

Discussion (0)

More to read

DeepSeek Open-Sources DeepInfer, the Inference Framework Behind DeepSeek-V4.1-Flash

What inference engine and KV offload engine do you use and why?

Ask HN: Non-deterministic leet code small LLM challenge site?