---
format: "aidr-story-markdown/v1"
id: "5f8a8265046e37da071574747da4324bd78a5984287c03b0d9922b257e2b812e"
canonical_url: "https://aidr.today/5f8a8265?lang=en"
title: "GLM 5.3 FlashX Hits 200 Tokens Per Second at 2.5X Price"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-21T17:08:41.000Z"
category: "Models"
topics: ["glm","inference","open-source","fine-tuning","perplexity","tool-call","training","reasoning"]
source_urls: ["https://marketbrief.now/ai/glm-53-flashx-hits-200-tokens-per-second-at-25x-price-cbf291d4","https://huggingnews.com/ai/glm-53-flashx-hits-200-tokens-per-second-at-25x-price-cbf291d4","https://huggingnews.com/ai/perplexity-cuts-glm-52-tool-call-failures-212percent-in-live-ab-tests-0d0b9728","https://marketbrief.now/ai/perplexity-cuts-glm-52-tool-call-failures-212percent-in-live-ab-tests-0d0b9728"]
summary: "Zixuan Li announced the launch of a high-speed variant of the GLM Flash model for developers and enterprise users. The glm-5.3-flashx model provides throughput…"
---

# GLM 5\.3 FlashX Hits 200 Tokens Per Second at 2\.5X Price

> [Open the canonical story](<https://aidr.today/5f8a8265?lang=en>)

**Published:** 2026-09-21T17:08:41.000Z
**Category:** Models
**Topics:** glm, inference, open\-source, fine\-tuning, perplexity, tool\-call, training, reasoning

## Summary

Zixuan Li announced the launch of a high\-speed variant of the GLM Flash model for developers and enterprise users\. The glm\-5\.3\-flashx model provides throughput…

## Sources

- [Story source](<https://marketbrief.now/ai/glm-53-flashx-hits-200-tokens-per-second-at-25x-price-cbf291d4>)
- [Story source](<https://huggingnews.com/ai/glm-53-flashx-hits-200-tokens-per-second-at-25x-price-cbf291d4>)
- [Story source](<https://huggingnews.com/ai/perplexity-cuts-glm-52-tool-call-failures-212percent-in-live-ab-tests-0d0b9728>)
- [Story source](<https://marketbrief.now/ai/perplexity-cuts-glm-52-tool-call-failures-212percent-in-live-ab-tests-0d0b9728>)