Live briefing: GLM-5.3, with Artificial Analysis. Sept 8, 11 AM PT. Save your seat

Blog

Inference engineering

All Research Model performance AI engineering Infrastructure News Community AI models Product Foundations

Model performance

Making Kimi K3 tokenization 18x faster for million-token agentic workloads

Michael Feil

Michael Feil

Making Kimi K3 tokenization 18x faster for million-token agentic workloads

Model performance

How to build a day-0 API for Kimi K3

Baseten symbol

Model Performance Team

How to build a day zero API for Kimi K3

Model performance

How we built the new fastest API for GLM-5.2

Alex Korte

Magdy Saleh

Tri Dao

Anant Desai

Bryce Dubayah

Abu Qader

Philip Kiely

Alex Korte

6 others

Baseten’s GLM-5.2 API is benchmarked at 601 tokens per second on Artificial Analysis, higher than any competing API

News

Introducing GLM-5.2 Fast

Abu Qader

Philip Kiely

Alina Weinstein

Abu Qader

2 others

Baseten's Fast GLM-5.2 endpoint

Community

How to choose an AI model: lessons from Notion and Gamma

Chloe Florit

How to choose an AI model

Model performance

How to optimize LLM inference speed and reduce costs in production

Chloe Florit

LLM inference optimizations

Infrastructure

H100 vs. H200 GPUs

Chloe Florit

H100 vs. H200

AI models

GLM 5.2 with vision

Harry Partridge

Model performance

Real-time video generation inference on Baseten

Ali Taha

Brendan Duke

Yikai Zhu

Faraz Shahsavan

Pankaj Gupta

Philip Kiely

Ali Taha

5 others

Real-time video generation inference

1 2 3 4...27