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
Alibabaalibaba/fp8fp8	Healthy	100%	99.02%	1.91s	3.73s	52 tps	203K	$1.33 / $4.18
AtlasCloudatlas-cloud/fp8fp8	Healthy	100%	99.29%	1.44s	5.31s	54 tps	203K	$1.26 / $3.96
Baidubaidu/fp8fp8	Healthy	100%	99.26%	947ms	3.70s	60 tps	203K	$0.896 / $2.82
Crusoecrusoe/fp8fp8	Healthy	100%	99.53%	470ms	3.37s	83 tps	203K	$1.20 / $4.40
DeepInfradeepinfra/fp4fp4	Healthy	100%	98.20%	1.01s	11.0s	35 tps	203K	$1.05 / $3.50
Friendlifriendli	Healthy	100%	99.74%	228ms	5.57s	78 tps	203K	$1.40 / $4.40
GMICloudgmicloud/fp8fp8	Healthy	100%	98.81%	1.93s	6.84s	55 tps	203K	$0.910 / $2.86
SiliconFlowsiliconflow/fp8fp8	Healthy	100%	99.48%	1.80s	6.39s	43 tps	205K	$1.19 / $3.74
StreamLakestreamlake/fp8fp8	Healthy	100%	98.15%	1.92s	8.54s	27 tps	200K	$0.966 / $3.04
Z.AIz-ai/fp8fp8	Healthy	99.14%	98.43%	9.15s	12.3s	23 tps	203K	$1.40 / $4.40
Chuteschutes/fp8fp8	Down	81.03%	88.74%	2.63s	44.4s	31 tps	203K	$0.980 / $3.08
Phalaphala	Down	73.17%	87.59%	2.57s	21.6s	28 tps	203K	$1.21 / $4.20
DigitalOceandigitalocean	Degraded	—	89.65%	1.43s	62.4s	14 tps	164K	$0.975 / $4.30
Nebiusnebius/fp8fp8	No data	—	94.91%	655ms	15.6s	29 tps	203K	$1.40 / $4.40
Novitanovita/fp8fp8	No data	—	98.92%	2.32s	7.40s	40 tps	205K	$1.38 / $4.40
Parasailparasail/fp8fp8	No data	—	99.73%	—	—	—	203K	$1.40 / $4.40
Venicevenice/fp8fp8	No data	—	91.81%	1.35s	19.4s	48 tps	200K	$1.54 / $4.84

Alibaba100%
Healthy24h 99.02%
p50
1.91s
p99
3.73s
Throughput
52 tps
Context
203K
$/Mtok
$1.33 / $4.18
alibaba/fp8fp8
AtlasCloud100%
Healthy24h 99.29%
p50
1.44s
p99
5.31s
Throughput
54 tps
Context
203K
$/Mtok
$1.26 / $3.96
atlas-cloud/fp8fp8
Baidu100%
Healthy24h 99.26%
p50
947ms
p99
3.70s
Throughput
60 tps
Context
203K
$/Mtok
$0.896 / $2.82
baidu/fp8fp8
Crusoe100%
Healthy24h 99.53%
p50
470ms
p99
3.37s
Throughput
83 tps
Context
203K
$/Mtok
$1.20 / $4.40
crusoe/fp8fp8
DeepInfra100%
Healthy24h 98.20%
p50
1.01s
p99
11.0s
Throughput
35 tps
Context
203K
$/Mtok
$1.05 / $3.50
deepinfra/fp4fp4
Friendli100%
Healthy24h 99.74%
p50
228ms
p99
5.57s
Throughput
78 tps
Context
203K
$/Mtok
$1.40 / $4.40
friendli
GMICloud100%
Healthy24h 98.81%
p50
1.93s
p99
6.84s
Throughput
55 tps
Context
203K
$/Mtok
$0.910 / $2.86
gmicloud/fp8fp8
SiliconFlow100%
Healthy24h 99.48%
p50
1.80s
p99
6.39s
Throughput
43 tps
Context
205K
$/Mtok
$1.19 / $3.74
siliconflow/fp8fp8
StreamLake100%
Healthy24h 98.15%
p50
1.92s
p99
8.54s
Throughput
27 tps
Context
200K
$/Mtok
$0.966 / $3.04
streamlake/fp8fp8
Z.AI99.14%
Healthy24h 98.43%
p50
9.15s
p99
12.3s
Throughput
23 tps
Context
203K
$/Mtok
$1.40 / $4.40
z-ai/fp8fp8
Chutes81.03%
Down24h 88.74%
p50
2.63s
p99
44.4s
Throughput
31 tps
Context
203K
$/Mtok
$0.980 / $3.08
chutes/fp8fp8
Phala73.17%
Down24h 87.59%
p50
2.57s
p99
21.6s
Throughput
28 tps
Context
203K
$/Mtok
$1.21 / $4.20
phala
DigitalOcean—
Degraded24h 89.65%
p50
1.43s
p99
62.4s
Throughput
14 tps
Context
164K
$/Mtok
$0.975 / $4.30
digitalocean
Nebius—
No data24h 94.91%
p50
655ms
p99
15.6s
Throughput
29 tps
Context
203K
$/Mtok
$1.40 / $4.40
nebius/fp8fp8
Novita—
No data24h 98.92%
p50
2.32s
p99
7.40s
Throughput
40 tps
Context
205K
$/Mtok
$1.38 / $4.40
novita/fp8fp8
Parasail—
No data24h 99.73%
p50
—
p99
—
Throughput
—
Context
203K
$/Mtok
$1.40 / $4.40
parasail/fp8fp8
Venice—
No data24h 91.81%
p50
1.35s
p99
19.4s
Throughput
48 tps
Context
200K
$/Mtok
$1.54 / $4.84
venice/fp8fp8

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.

History

4 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, averaged over the hour.

Throughput

Median tokens per second.