GLM 5.1

z-ai/glm-5.1

Compare with GLM 5, GLM 5 Turbo, GLM 5V Turbo

CompareGLM 5.1

Provider	State	Uptime 5m	24h	p50 latency	p99	Throughput	Context	$/Mtok
AtlasCloudatlas-cloud/fp8fp8	Healthy	100%	99.50%	1.42s	6.91s	52 tps	203K	$1.26 / $3.96
Baidubaidu/fp8fp8	Healthy	100%	99.73%	1.30s	3.80s	59 tps	203K	$0.896 / $2.82
Crusoecrusoe/fp8fp8	Degraded	100%	99.67%	466ms	4.86s	78 tps	203K	$1.20 / $4.40
Friendlifriendli	Healthy	100%	99.92%	259ms	8.04s	63 tps	203K	$1.40 / $4.40
Nebiusnebius/fp8fp8	Degraded	100%	94.60%	841ms	27.2s	25 tps	203K	$1.40 / $4.40
SiliconFlowsiliconflow/fp8fp8	Healthy	100%	99.82%	2.13s	8.50s	41 tps	205K	$1.19 / $3.74
StreamLakestreamlake/fp8fp8	Healthy	100%	98.13%	2.38s	9.10s	24 tps	200K	$0.966 / $3.04
Z.AIz-ai/fp8fp8	Degraded	98.68%	98.68%	8.37s	13.3s	21 tps	203K	$1.40 / $4.40
Alibabaalibaba/fp8fp8	Degraded	—	99.73%	2.04s	9.78s	50 tps	203K	$1.33 / $4.18
Chuteschutes/fp8fp8	Down	—	87.03%	3.10s	65.6s	26 tps	203K	$0.980 / $3.08
DeepInfradeepinfra/fp4fp4	No data	—	97.73%	1.33s	636s	26 tps	203K	$1.05 / $3.50
DigitalOceandigitalocean	Down	—	91.14%	1.58s	45.4s	14 tps	164K	$0.975 / $4.30
GMICloudgmicloud/fp8fp8	Down	—	99.28%	2.86s	12.6s	49 tps	203K	$0.910 / $2.86
Novitanovita/fp8fp8	No data	—	99.67%	2.44s	6.37s	43 tps	205K	$1.38 / $4.40
Parasailparasail/fp8fp8	No data	—	99.68%	—	—	—	203K	$1.40 / $4.40
Phalaphala	Down	—	87.24%	4.33s	652s	25 tps	203K	$1.21 / $4.20
Venicevenice/fp8fp8	Down	—	90.55%	3.39s	47.9s	20 tps	200K	$1.54 / $4.84

AtlasCloud100%
Healthy24h 99.50%
p50
1.42s
p99
6.91s
Throughput
52 tps
Context
203K
$/Mtok
$1.26 / $3.96
atlas-cloud/fp8fp8
Baidu100%
Healthy24h 99.73%
p50
1.30s
p99
3.80s
Throughput
59 tps
Context
203K
$/Mtok
$0.896 / $2.82
baidu/fp8fp8
Crusoe100%
Degraded24h 99.67%
p50
466ms
p99
4.86s
Throughput
78 tps
Context
203K
$/Mtok
$1.20 / $4.40
crusoe/fp8fp8
Friendli100%
Healthy24h 99.92%
p50
259ms
p99
8.04s
Throughput
63 tps
Context
203K
$/Mtok
$1.40 / $4.40
friendli
Nebius100%
Degraded24h 94.60%
p50
841ms
p99
27.2s
Throughput
25 tps
Context
203K
$/Mtok
$1.40 / $4.40
nebius/fp8fp8
SiliconFlow100%
Healthy24h 99.82%
p50
2.13s
p99
8.50s
Throughput
41 tps
Context
205K
$/Mtok
$1.19 / $3.74
siliconflow/fp8fp8
StreamLake100%
Healthy24h 98.13%
p50
2.38s
p99
9.10s
Throughput
24 tps
Context
200K
$/Mtok
$0.966 / $3.04
streamlake/fp8fp8
Z.AI98.68%
Degraded24h 98.68%
p50
8.37s
p99
13.3s
Throughput
21 tps
Context
203K
$/Mtok
$1.40 / $4.40
z-ai/fp8fp8
Alibaba—
Degraded24h 99.73%
p50
2.04s
p99
9.78s
Throughput
50 tps
Context
203K
$/Mtok
$1.33 / $4.18
alibaba/fp8fp8
Chutes—
Down24h 87.03%
p50
3.10s
p99
65.6s
Throughput
26 tps
Context
203K
$/Mtok
$0.980 / $3.08
chutes/fp8fp8
DeepInfra—
No data24h 97.73%
p50
1.33s
p99
636s
Throughput
26 tps
Context
203K
$/Mtok
$1.05 / $3.50
deepinfra/fp4fp4
DigitalOcean—
Down24h 91.14%
p50
1.58s
p99
45.4s
Throughput
14 tps
Context
164K
$/Mtok
$0.975 / $4.30
digitalocean
GMICloud—
Down24h 99.28%
p50
2.86s
p99
12.6s
Throughput
49 tps
Context
203K
$/Mtok
$0.910 / $2.86
gmicloud/fp8fp8
Novita—
No data24h 99.67%
p50
2.44s
p99
6.37s
Throughput
43 tps
Context
205K
$/Mtok
$1.38 / $4.40
novita/fp8fp8
Parasail—
No data24h 99.68%
p50
—
p99
—
Throughput
—
Context
203K
$/Mtok
$1.40 / $4.40
parasail/fp8fp8
Phala—
Down24h 87.24%
p50
4.33s
p99
652s
Throughput
25 tps
Context
203K
$/Mtok
$1.21 / $4.20
phala
Venice—
Down24h 90.55%
p50
3.39s
p99
47.9s
Throughput
20 tps
Context
200K
$/Mtok
$1.54 / $4.84
venice/fp8fp8

Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

3 endpoints reporting no data are omitted from the charts.

Availability

Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.

Time to first token

Logarithmic axis — the fleet spans two orders of magnitude. p50 and p99 are OpenRouter's rolling 30-minute windows.

Throughput

Median tokens per second.