智谱 AI

Zhipu AI provides the GLM series of large language models including GLM-4, ChatGLM, and CodeGeeX for text, code, and multimodal tasks.

Health Check

100%Recent availability

History (72 pts)

PastNow

Model	Speed	Latency	Tests
glm-z1-airx	168.24 t/s	0.34s	5
GLM-4.6V-Flash	142.21 t/s	9.86s	25
GLM-4.6V-Flash	142.21 t/s	9.86s	25
GLM-4.6V-Flash	142.21 t/s	9.86s	25
glm-z1-flash	125.12 t/s	0.34s	10
glm-4.1v-thinking-flash	113.85 t/s	7.10s	5
glm-4.1v-thinking-flash	113.85 t/s	7.10s	5
GLM-4.7-Flash	88.52 t/s	12.70s	5
glm-4.5-x	72.08 t/s	9.25s	10
glm-4.5-x	72.08 t/s	9.25s	10
glm-4.5-air	72.07 t/s	5.79s	20
glm-4.5-air	72.07 t/s	5.79s	20
glm-4-flashx	71.64 t/s	0.29s	5
glm-4.5-airx	70.70 t/s	11.56s	5
glm-4.5-airx	70.70 t/s	11.56s	5
GLM-4-FlashX	65.32 t/s	0.43s	10
glm-4.5	53.23 t/s	9.63s	20
glm-4.5	53.23 t/s	9.63s	20
GLM-4.7-FlashX	53.18 t/s	22.27s	5
glm-z1-air	52.65 t/s	0.30s	5

Showing 20 of 41 models.

Time	Model	Speed	Latency
Apr 8, 02:10 PM	glm-5.1	56.71 t/s	13.10s
Apr 8, 03:39 AM	glm-5.1	36.80 t/s	19.39s
Apr 7, 07:34 AM	glm-5	34.83 t/s	31.15s
Apr 7, 07:18 AM	glm-5.1	27.04 t/s	20.87s
Apr 4, 11:24 AM	glm-4-flash-250414	39.15 t/s	0.41s
Apr 4, 11:16 AM	glm-4-flash	27.97 t/s	0.51s
Apr 2, 02:00 PM	glm-4.5	55.73 t/s	5.36s
Apr 1, 02:01 AM	glm-5	0.00 t/s	0.00s
Apr 1, 02:00 AM	glm-5-turbo	0.00 t/s	0.00s
Mar 31, 03:49 AM	glm-5.1	28.63 t/s	15.20s