← Blog
ANNOUNCEMENT

GLM-5.3 FlashX is live in Command Code

GLM-5.3 FlashX is now live in Command Code. High speed variant of GLM-5.3 Flash. 200 TPS with 1M context window

Team Command Code
2 min read
Sep 19, 2026

GLM-5.3 FlashX is now live in Command Code.

  • High speed variant of GLM-5.3 Flash
  • ~200 TPS with 1M context window
  • Multimodal (text, image, video)

Available across all plans and API.

GLM-5.3 FlashX at a glance

High-speed GLM-5.3 Flash with 1M context.

SpecGLM-5.3 FlashX
Model IDz-ai/glm-5.3-flashx
Context window1M tokens
ReleasedSeptember 18, 2026
Input$0.37 per 1M tokens
Output$1.25 per 1M tokens
Cache read$0.07 per 1M tokens
Effective input in an agent loop$0.16 per 1M tokens
PlansGo and above

Specs, pricing and plans are from the GLM-5.3 FlashX model page as of September 28, 2026, including any deal running that day, so they can differ from the launch pricing above. Intelligence and Coding Index scores are from Artificial Analysis.

Use GLM-5.3 FlashX

1cmd --model z-ai/glm-5.3-flashx

Or type /model in a session and pick it. You can switch mid-session without losing context.

What real work costs on GLM-5.3 FlashX

TaskTokens (in · out)Cost
Quick lookup / one-liner8K · 1K$0.0021
Review a 500-line PR60K · 4K$0.01
Fix a bug (agent loop)180K · 12K$0.04
Refactor a module320K · 20K$0.08
Full-repo agent run900K · 45K$0.18

Try Command Code

The best coding agent for open models, in your terminal or on your desktop.

1npm i -g command-code

Desktop App · Docs · X · Discord

Share this article