88Z AI, 18 September — Zhipu has released GLM-5.3-FlashX, achieving inference speeds of up to 200 tokens/s. Previously introduced as Ox Alpha, the model is built on the computing power of 100,000 domestic chips, with enhanced infrastructure investment and inference optimization. As a leading model in intelligence for its size, the GLM-5.3-Flash series offers high cost-effectiveness, and this upgrade further strengthens its comprehensive competitiveness in intelligence, price, and speed.
At a glance
- GLM-5.3-FlashX reaches up to 200 tokens/s inference speed, powered by 100,000 domestic chips.
- The model enhances speed competitiveness while maintaining top-tier intelligence and cost-effectiveness for its size.
The update
Zhipu AI has officially launched the GLM-5.3-FlashX model, which achieves a maximum inference speed of 200 tokens per second. Previously available to global developers under the codename "Ox Alpha," the model saw continuous growth in usage volume. The new model leverages robust inference computing power from 100,000 domestic chips, marking increased investment in infrastructure and deep optimization of inference performance. The GLM-5.3-Flash series has long maintained the highest level of intelligence among models of its size and is known for its high cost-effectiveness. With significant speed improvements, the new FlashX version enhances comprehensive competitiveness across intelligence, pricing, and response speed, offering users a more efficient option.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- 智谱Source published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.