z-aitext + image + video → text
Z.ai: GLM 5.3 FlashX
Canonical ID: z-ai/glm-5.3-flashx
GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...
Artificial Analysis Benchmarks
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.37
Completion Output (1M Tokens)
Output$1.25
Prompt KV-Cache Read (1M Tokens)
Cached$0.07
Context Window Capacity
Context1,024k tokens
Supported Parameters & Features
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p