GLM-5.3-FlashX

by Z.AI · 320B (A18B) parameters

Current new · 25d budget open weights cheap tier

Email me when GLM-5.3-FlashX gets cheaper

Today's price · per 1M tokens

Input

$0.370

per 1M tokens

Output

$1.25

per 1M tokens

Blended

$0.590

blended $/1M — 3:1 weighted input:output

Cached input

$0.075

20% of input — prompt caching

How this price is scoped: Standard list pricing, per 1M tokens. Z.AI's own rate card (docs.z.ai/guides/overview/pricing) prints one value per cell for GLM-5.3-FlashX under "Latest Models" — input $0.37, cached input $0.075, output $1.25 — with no discounted/struck-through pair of the kind it showed throughout the GLM-5.3-Flash launch promotion, and Z.AI's own OpenRouter endpoint reports discount 0. Cached-input STORAGE is separately labelled "Limited-time Free" with no end date, and is not a rate we publish.

Source: official Z.AI pricing · read Sep 19, 2026 MODELPRICEWATCH.COM · 2026-09-19

Price receipt

We read Z.AI's own pricing page on Sep 19, 2026 and found GLM-5.3-FlashX listed with a price on the same row — that read is where the number above comes from, recorded as a new model. We keep the page text we read; its content hash is 63526bfdd8.

Overview

The 200 tokens/s serving tier of GLM-5.3-Flash rather than a separate model — Z.AI documents the pair on one page and publishes no standalone FlashX model card. 320B total / 18B activated, 1M-token context, 128K max output, thinking always on, and video, image, text and file input. $0.37/$1.25 per 1M tokens with cached input at $0.075 — roughly 2.5x plain GLM-5.3-Flash for the same MIT-licensed weights at huggingface.co/zai-org/GLM-5.3-Flash.

Run it yourself