GLM-5.3-Highspeed: Zhipu's 490 TPS speed tier in ZCode gray release
Zhipu is gray-releasing GLM-5.3-Highspeed to a random subset of ZCode subscribers — a speed-optimized GLM-5.3 tier reportedly sustaining around 490 tokens/sec for long agent runs.
Why it matters
If the ~490 TPS figure holds, it would reset the output-speed ceiling among major provider APIs, making long multi-hour agent sessions meaningfully shorter to sit through.
What you could build with it
A startup could build a live pair-programming companion that streams whole-file refactors in seconds rather than minutes, charging per active coding session and using the speed tier to keep engineers in flow.
Does it hold up?
Too early to judge: randomized gray release to ZCode subscribers with no opt-in and no official benchmark sheet; the 490 TPS figure is a single community screenshot, and Z.ai's official docs still list only GLM-5.3 and GLM-5.3-Flash.
Built with GLM-5.3-Highspeed
- Zhipu Releases Ultra-Fast New Model — GLM-5.3 Highspeeddeepseekv4pro.com · Independent summary: no launch post, just users noticing the new name in the ZCode model list; 490 tokens/sec from one early user's screenshot; Omen Alpha connection unverified.
Learn more
First spotted on article: source.
More AI models
OpenAI publishes 722 AI-generated math manuscripts from an unreleased modelOpenAI released 722 mathematical manuscripts in 372 result families to GitHub under Apache-2.0, produced by an…models · JEV 0.74Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73StepFun Step-5-Preview — open BF16 weights releasedStepFun published the full BF16 weights for its flagship Step-5-Preview agentic model (600B-parameter sparse MoE, 27B…models · JEV 0.73NVIDIA Nemotron 3.5 Retriever collection: Embed 8B/1B, Rerank 8B, Parse 631MNVIDIA's Oct 21 collection drop for agentic retrieval: Nemotron-3.5-Embed in 8B BF16, 1B BF16 and 1B NVFP4…models · JEV 0.72Kimi K3.1 Pro: Moonshot's 2.8T open-weight flagship officially launchesMoonshot AI officially launched Kimi K3.1 Pro on Oct 23, a mixture-of-experts model with 2.8 trillion total / 104…models · JEV 0.72
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.