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.
Related event: Z.ai Releases Open-Weight GLM-5.3 with Day-One Adoption Across Platforms(19 posts)→
More from coding & agent
- A versioned bootstrap loader pattern for keeping AI-generated code always shippable — NickPassig · 2026-10-15
- Amazon blocks AI shopping agents; Maritime offers $1/month Android MCP workaround — Scobleizer · 2026-10-15
- Dev vibe-codes open-source newsletter platform, 83% cheaper than Beehiiv from $19/mo — marclou · 2026-10-15
- ERP AI launches Proto: 'headless SaaS' business software built for AI agents — Aiden_Tech_Ai · 2026-10-15
- Engineering managers need deep reading, not just agent summaries: 5 recommended resources — rseroter · 2026-10-15
- Adding motion graphics with just a prompt: the Claude Motion x ElevenLabs MCP workflow — CurieuxExplorer · 2026-10-15