GLM-5.3-FlashX

Closed Active Multimodal Hybrid glm-5-3-flashx

High-speed API tier of GLM-5.3-Flash at about 200 tokens per second.

Released
Aug 26, 2026
Context window
1M tokens
Max output
131K tokens
Parameters
320B 18B active
Input price
$0.37 per 1M
Output price
$1.25 per 1M

Prices are first-party list prices in USD at the standard tier. Last verified Oct 30, 2026.

Pricing

Launch priceAug 26, 2026
$0.37 in / $1.25 out
Current price since Aug 26, 2026
$0.37 in / $1.25 out
Cached input $0.075 per 1M

Specifications

Developer
Z.ai (Zhipu AI)
Model type
Multimodal
Architecture
Hybrid
Parameters
320B (18B active)
Input
Text Image Video
Output
Text
Knowledge cutoff
Not disclosed
License
Proprietary
API access
First-party API
Capabilities
Agentic Coding Vision