Reinforcement Learning Agent runtime infrastructure GLM Model serving Cost Optimization Benchmarks DeepSeek V4 Flash Interpretability Security

Baseten

The inference platform for AI products.

Visit site

A production AI inference platform for deploying, serving, scaling, and operating machine-learning and generative-AI models through APIs and managed infrastructure.

Recent stories

4 linked stories

releaseSECONDARY2026-10-09

Baseten launches Project Beacon safety monitoring for open models

Baseten's Project Beacon integrates Goodfire activation monitors into inference to flag unsafe model behavior. Teams can configure responses to prompt injection, policy violations, sensitive-data exposure and cyber misuse.

releaseSECONDARY2026-08-03

DeepSeek V4 Flash adds Baseten and Together AI serving with 1M-token context

Baseten and Together AI added DeepSeek V4 Flash with a 1M-token context window, reasoning-effort controls, and DSpark decoding. ValsAI ranked it the cheapest model above 60 on its index, and Nous promoted a short 90% discount.

newsSECONDARY2026-06-22

GLM-5.2 adds Perplexity Agent API and Droid support on Baseten at >280 TPS

GLM-5.2 added Perplexity Agent API, Droid, and more hosting options, while Baseten reported over 280 TPS and sub-0.8s TTFT. Builders should watch the cost and benchmark data as it moves into production agent stacks.

releaseSECONDARY2026-05-27

Trajectory launches continual-learning platform with off-policy SDPO

Trajectory launched a platform that turns agent traces and user corrections into post-deployment model updates instead of prompt-only fixes. Baseten and Tinker described live A/B post-training, 397B-model deployment work, and an off-policy recipe for stabilizing the loop.