GLM-5.3 on Cloudflare Workers AI: Doubles Long-Horizon Coding Performance
michellechen · x · 2026-08-29
Z.ai GLM-5.3 is now available on Cloudflare Workers AI, designed for long-running, tool-driven workflows.
Performance:
- Terminal Bench 3.0: 28.3 (up from 4.6, open-source SOTA).
- SWE-Marathon: 42.5 (up from 19.4).
Pricing:
- Input: $1.40/M, Cached: $0.26/M, Output: $4.40/M (same as 5.2).
Usage: Requires Workers Paid plan; supports bindings, REST API, and OpenAI compatibility.
More from Infra
- Data Centers Drive Rate Hikes as US Utilities Cut Residential Rebates — NathanpmYoung · 2026-08-29
- User recommends Unsloth dynamic q2_k_xl for Qwen3.8 27B — cephaloform · 2026-08-29
- AWS Multi-Node EFA Memory Leak Fixed in Build 1.50 — StasBekman · 2026-08-29
- Grass: Unlocking High-Quality AI Training Data via Crowdsourcing — grass · 2026-08-29
- Practical use of 2bit quantization: Running LLMs on low-end laptops — cephaloform · 2026-08-29
- Running Qwen3.8-27B with 128K context on RTX 4000 Blackwell — mmkaywhatevers · 2026-08-29