Z.AI

14 endpoints · all healthy · worst uptime 98.61%

	State
GLM 4.5 Airz-ai/fp8fp8	Healthy	100%	99.86%	99.46%	98.63%	1.09s	5.87s	66 tps	131K	$0.200 / $1.10
GLM 4.6Vz-ai/fp8fp8	Healthy	100%	99.58%	99.07%	97.95%	2.34s	13.6s	37 tps	131K	$0.300 / $0.900
GLM 5z-ai/fp8fp8	Healthy	100%	99.98%	99.94%	99.93%	6.16s	10.3s	64 tps	203K	$1.00 / $3.20
GLM 5.1z-ai/fp8fp8	Healthy	100%	99.92%	99.70%	99.67%	8.88s	11.8s	24 tps	203K	$1.40 / $4.40
GLM 5.2z-ai/fp8fp8	Healthy	100%	99.75%	99.80%	99.77%	3.21s	15.7s	62 tps	1.0M	$1.40 / $4.40
GLM 5.3 FlashXz-ai/fp8fp8	Healthy	100%	99.98%	99.99%	99.99%	2.35s	9.41s	73 tps	1.0M	$0.370 / $1.25
GLM 5.3z-ai/fp8fp8	Healthy	99.94%	99.86%	99.91%	99.89%	2.88s	21.3s	45 tps	1.0M	$1.40 / $4.40
GLM 4.7z-ai/fp4fp4	Healthy	99.90%	99.89%	99.68%	93.00%	8.80s	11.3s	26 tps	203K	$0.600 / $2.20
GLM 5.3 Flashz-ai/fp8fp8	Healthy	98.61%	99.52%	99.68%	98.96%	4.23s	16.5s	28 tps	1.0M	$0.150 / $0.500
GLM 4.5z-ai/fp8fp8	No data	—	99.99%	100%	99.99%	8.43s	17.0s	26 tps	131K	$0.600 / $2.20
GLM 4.5Vz-ai/fp8fp8	No data	—	98.87%	99.45%	97.48%	829ms	11.6s	71 tps	66K	$0.600 / $1.80
GLM 4.6z-ai/fp4fp4	No data	—	99.54%	99.36%	91.12%	8.49s	14.9s	27 tps	203K	$0.600 / $2.20
GLM 5 Turboz-ai	No data	—	99.99%	99.96%	99.99%	8.18s	27.0s	26 tps	203K	$1.20 / $4.00
GLM 5V Turboz-ai/fp8fp8	No data	—	99.98%	99.98%	99.99%	2.96s	35.3s	27 tps	203K	$1.20 / $4.00

GLM 4.5 Air100%
Healthy24h 99.86%
7d
99.46%
30d
98.63%
p50
1.09s
p99
5.87s
Throughput
66 tps
Context
131K
$/Mtok
$0.200 / $1.10
z-ai/fp8fp8
GLM 4.6V100%
Healthy24h 99.58%
7d
99.07%
30d
97.95%
p50
2.34s
p99
13.6s
Throughput
37 tps
Context
131K
$/Mtok
$0.300 / $0.900
z-ai/fp8fp8
GLM 5100%
Healthy24h 99.98%
7d
99.94%
30d
99.93%
p50
6.16s
p99
10.3s
Throughput
64 tps
Context
203K
$/Mtok
$1.00 / $3.20
z-ai/fp8fp8
GLM 5.1100%
Healthy24h 99.92%
7d
99.70%
30d
99.67%
p50
8.88s
p99
11.8s
Throughput
24 tps
Context
203K
$/Mtok
$1.40 / $4.40
z-ai/fp8fp8
GLM 5.2100%
Healthy24h 99.75%
7d
99.80%
30d
99.77%
p50
3.21s
p99
15.7s
Throughput
62 tps
Context
1.0M
$/Mtok
$1.40 / $4.40
z-ai/fp8fp8
GLM 5.3 FlashX100%
Healthy24h 99.98%
7d
99.99%
30d
99.99%
p50
2.35s
p99
9.41s
Throughput
73 tps
Context
1.0M
$/Mtok
$0.370 / $1.25
z-ai/fp8fp8
GLM 5.399.94%
Healthy24h 99.86%
7d
99.91%
30d
99.89%
p50
2.88s
p99
21.3s
Throughput
45 tps
Context
1.0M
$/Mtok
$1.40 / $4.40
z-ai/fp8fp8
GLM 4.799.90%
Healthy24h 99.89%
7d
99.68%
30d
93.00%
p50
8.80s
p99
11.3s
Throughput
26 tps
Context
203K
$/Mtok
$0.600 / $2.20
z-ai/fp4fp4
GLM 5.3 Flash98.61%
Healthy24h 99.52%
7d
99.68%
30d
98.96%
p50
4.23s
p99
16.5s
Throughput
28 tps
Context
1.0M
$/Mtok
$0.150 / $0.500
z-ai/fp8fp8
GLM 4.5—
No data24h 99.99%
7d
100%
30d
99.99%
p50
8.43s
p99
17.0s
Throughput
26 tps
Context
131K
$/Mtok
$0.600 / $2.20
z-ai/fp8fp8
GLM 4.5V—
No data24h 98.87%
7d
99.45%
30d
97.48%
p50
829ms
p99
11.6s
Throughput
71 tps
Context
66K
$/Mtok
$0.600 / $1.80
z-ai/fp8fp8
GLM 4.6—
No data24h 99.54%
7d
99.36%
30d
91.12%
p50
8.49s
p99
14.9s
Throughput
27 tps
Context
203K
$/Mtok
$0.600 / $2.20
z-ai/fp4fp4
GLM 5 Turbo—
No data24h 99.99%
7d
99.96%
30d
99.99%
p50
8.18s
p99
27.0s
Throughput
26 tps
Context
203K
$/Mtok
$1.20 / $4.00
z-ai
GLM 5V Turbo—
No data24h 99.98%
7d
99.98%
30d
99.99%
p50
2.96s
p99
35.3s
Throughput
27 tps
Context
203K
$/Mtok
$1.20 / $4.00
z-ai/fp8fp8

Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

GLM 4.6 z-ai/fp4

GLM 4.5V z-ai/fp8

GLM 4.7 z-ai/fp4

GLM 4.5 Air z-ai/fp8

GLM 4.6V z-ai/fp8

GLM 5.3 Flash z-ai/fp8

GLM 5.1 z-ai/fp8

GLM 5.2 z-ai/fp8

GLM 5 z-ai/fp8

GLM 5.3 z-ai/fp8

GLM 4.5 z-ai/fp8

GLM 5V Turbo z-ai/fp8

GLM 5 Turbo z-ai

GLM 5.3 FlashX z-ai/fp8

Colour by 12-hourly mean uptime:≥ 95%90–95%< 90%no data

Through the live last bucket (raw rounds, updated every collection round) · 14 endpoints with data, sorted worst-first.