GLM-5.3 launches on Baseten with major coding gains and 1M context
baseten · x · 2026-08-29
GLM-5.3 is now live on Baseten Model APIs (US only).
Key Updates:
- Architecture: Runs on the same 744B-A40B MoE base as GLM-5.2, with capability gains driven by scaled post-training on realistic environments like full codebases, docs, and testing tools.
- Coding: Significant coding improvements, with Terminal-Bench 3.0 jumping from 4.6% to 28.3% over GLM-5.2, plus better security analysis.
- Agentic: Supports three thinking effort levels (low, high, max) for sustained planning and verification in agentic workflows.
- Context: 1M token context window.
- Pricing: Input $1.40/1M tokens, Cached input $0.14/1M tokens, Output $4.40/1M tokens.
More from coding & agent
- GLM-5.3 Launches on Tinker with 256k Context — simonguozirui · 2026-08-29
- Conifer SDK Open-Sourced: Unified Gateway with Exact Cost Tracking — ycombinator · 2026-08-29
- Browser Use launches iMessage web agents for booking and shopping — _AustinCalvert_ · 2026-08-29
- AgentHeights Gamifies Agentic Orchestration with Virtual Office — edgarpavlovsky · 2026-08-29
- From Single Screen to Multi-Step Tasks: A 7-Step Roadmap for Medical AI Agents — MaryamMiradi · 2026-08-29
- Prime Agent: A Self-Improving RLM Harness for Coding and Autonomous Tasks — xeophon · 2026-08-29