GLM-4.6V FlashX
Z.ai
🧠 Language Model
Lightweight vision model. Fast and cost-effective for image tasks.
Specifications
Input modalitiestext, image
Output modalitiestext
Capabilitiesreasoning, tools
Relative speed●●●●● Blazing
Context window128,000 tokens
Max output4,096 tokens
Vision inputYes
Tool callingYes
Input price$0.07 / 1M
Output price$0.7 / 1M
Pricing
$0.07 / 1M input tokens · $0.7 / 1M output tokens
Platform credit pricing — live rates on the Models page.