Seonglae ChoAI Optimization, Inference Optimization, Inference Engine
Fast inference but usually no API access to hidden states
Model Inference Tools
AI Server
Model Inference Servers
AI Inference Notion
AI Performance Libraries
LLM inference cost is going down fast
Welcome to LLMflation - LLM inference cost is going down fast ⬇️ | Andreessen Horowitz
For LLM of equivalent performance, the inference cost is decreasing by 10x every year. What cost $60/million tokens in 2021 costs $.06/million tokens today.
https://a16z.com/llmflation-llm-inference-cost
Inference cost with model size
Observations About LLM Inference Pricing — LessWrong
This work was done as part of the MIRI Technical Governance Team. It reflects my views and may not reflect those of the organization. …
https://www.lesswrong.com/posts/mRKd4ArA5fYhd2BPb/observations-about-llm-inference-pricing
What is moat
NeoSigma on Twitter / X
https://t.co/PDwGDe6d0y— NeoSigma (@neosigma_ai) July 17, 2026
https://x.com/neosigma_ai/status/2078159114254057612?s=20