GLM 5.1: providers compared

Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.

Current state

	State
AtlasCloudatlas-cloud/fp8fp8	Healthy	100%◆ (best)	99.69%	99.75%	99.75%	1.53s	13.8s	55 tps	203K	$1.26 / $3.96
Baidubaidu/fp8fp8	Healthy	100%◆ (best)	99.97%	99.90%	99.90%	1.28s	4.72s	60 tps	203K	$0.896 / $2.82◆ (best)
DigitalOceandigitalocean	Healthy	100%◆ (best)	97.31%	94.07%	94.07%	1.39s	22.1s	14 tps	164K	$1.30 / $4.30
Friendlifriendli	Healthy	100%◆ (best)	99.98%	99.96%◆ (best)	99.96%◆ (best)	239ms◆ (best)	3.69s◆ (best)	74 tps	203K	$1.40 / $4.40
Nebiusnebius/fp8fp8	Healthy	100%◆ (best)	98.21%	97.51%	97.51%	812ms	8.70s	28 tps	203K	$1.40 / $4.40
Parasailparasail/fp8fp8	Healthy	100%◆ (best)	98.91%	99.43%	99.43%	839ms	13.1s	89 tps◆ (best)	203K	$1.40 / $4.40
SiliconFlowsiliconflow/fp8fp8	Healthy	100%◆ (best)	99.95%	99.89%	99.89%	1.74s	10.2s	48 tps	205K	$1.19 / $3.74
StreamLakestreamlake/fp8fp8	Healthy	100%◆ (best)	99.51%	98.83%	98.83%	2.31s	9.94s	28 tps	200K	$0.966 / $3.04
Z.AIz-ai/fp8fp8	Healthy	100%◆ (best)	99.89%	99.09%	99.09%	3.96s	6.71s	23 tps	203K	$1.40 / $4.40
GMICloudgmicloud/fp8fp8	Healthy	97.73%	99.64%	99.63%	99.63%	1.71s	13.7s	63 tps	203K	$0.910 / $2.86
Alibabaalibaba/fp8fp8	No data	—	99.90%	99.77%	99.77%	1.91s	9.35s	48 tps	203K	$1.33 / $4.18
Chuteschutes/fp8fp8	Down	—	76.88%	83.27%	83.27%	3.26s	53.1s	25 tps	203K	$0.980 / $3.08
Crusoecrusoe/fp8fp8	No data	—	99.69%	99.44%	99.44%	577ms	15.6s	71 tps	203K	$1.20 / $4.40
DeepInfradeepinfra/fp4fp4	No data	—	99.69%	99.40%	99.40%	1.45s	17.7s	41 tps	203K	$1.05 / $3.50
Novitanovita/fp8fp8	No data	—	99.86%	99.34%	99.34%	2.93s	10.5s	36 tps	205K	$1.38 / $4.40
Phalaphala	No data	—	77.33%	84.04%	84.04%	3.84s	24.8s	25 tps	203K	$1.21 / $4.20
Venicevenice/fp8fp8	Down	—	97.86%	96.49%	96.49%	6.55s	17.5s	11 tps	200K	$1.54 / $4.84

AtlasCloud100%◆ (best)
Healthy24h 99.69%
7d
99.75%
30d
99.75%
p50
1.53s
p99
13.8s
Throughput
55 tps
Context
203K
$/Mtok
$1.26 / $3.96
atlas-cloud/fp8fp8
Baidu100%◆ (best)
Healthy24h 99.97%
7d
99.90%
30d
99.90%
p50
1.28s
p99
4.72s
Throughput
60 tps
Context
203K
$/Mtok
$0.896 / $2.82◆ (best)
baidu/fp8fp8
DigitalOcean100%◆ (best)
Healthy24h 97.31%
7d
94.07%
30d
94.07%
p50
1.39s
p99
22.1s
Throughput
14 tps
Context
164K
$/Mtok
$1.30 / $4.30
digitalocean
Friendli100%◆ (best)
Healthy24h 99.98%
7d
99.96%◆ (best)
30d
99.96%◆ (best)
p50
239ms◆ (best)
p99
3.69s◆ (best)
Throughput
74 tps
Context
203K
$/Mtok
$1.40 / $4.40
friendli
Nebius100%◆ (best)
Healthy24h 98.21%
7d
97.51%
30d
97.51%
p50
812ms
p99
8.70s
Throughput
28 tps
Context
203K
$/Mtok
$1.40 / $4.40
nebius/fp8fp8
Parasail100%◆ (best)
Healthy24h 98.91%
7d
99.43%
30d
99.43%
p50
839ms
p99
13.1s
Throughput
89 tps◆ (best)
Context
203K
$/Mtok
$1.40 / $4.40
parasail/fp8fp8
SiliconFlow100%◆ (best)
Healthy24h 99.95%
7d
99.89%
30d
99.89%
p50
1.74s
p99
10.2s
Throughput
48 tps
Context
205K
$/Mtok
$1.19 / $3.74
siliconflow/fp8fp8
StreamLake100%◆ (best)
Healthy24h 99.51%
7d
98.83%
30d
98.83%
p50
2.31s
p99
9.94s
Throughput
28 tps
Context
200K
$/Mtok
$0.966 / $3.04
streamlake/fp8fp8
Z.AI100%◆ (best)
Healthy24h 99.89%
7d
99.09%
30d
99.09%
p50
3.96s
p99
6.71s
Throughput
23 tps
Context
203K
$/Mtok
$1.40 / $4.40
z-ai/fp8fp8
GMICloud97.73%
Healthy24h 99.64%
7d
99.63%
30d
99.63%
p50
1.71s
p99
13.7s
Throughput
63 tps
Context
203K
$/Mtok
$0.910 / $2.86
gmicloud/fp8fp8
Alibaba—
No data24h 99.90%
7d
99.77%
30d
99.77%
p50
1.91s
p99
9.35s
Throughput
48 tps
Context
203K
$/Mtok
$1.33 / $4.18
alibaba/fp8fp8
Chutes—
Down24h 76.88%
7d
83.27%
30d
83.27%
p50
3.26s
p99
53.1s
Throughput
25 tps
Context
203K
$/Mtok
$0.980 / $3.08
chutes/fp8fp8
Crusoe—
No data24h 99.69%
7d
99.44%
30d
99.44%
p50
577ms
p99
15.6s
Throughput
71 tps
Context
203K
$/Mtok
$1.20 / $4.40
crusoe/fp8fp8
DeepInfra—
No data24h 99.69%
7d
99.40%
30d
99.40%
p50
1.45s
p99
17.7s
Throughput
41 tps
Context
203K
$/Mtok
$1.05 / $3.50
deepinfra/fp4fp4
Novita—
No data24h 99.86%
7d
99.34%
30d
99.34%
p50
2.93s
p99
10.5s
Throughput
36 tps
Context
205K
$/Mtok
$1.38 / $4.40
novita/fp8fp8
Phala—
No data24h 77.33%
7d
84.04%
30d
84.04%
p50
3.84s
p99
24.8s
Throughput
25 tps
Context
203K
$/Mtok
$1.21 / $4.20
phala
Venice—
Down24h 97.86%
7d
96.49%
30d
96.49%
p50
6.55s
p99
17.5s
Throughput
11 tps
Context
200K
$/Mtok
$1.54 / $4.84
venice/fp8fp8

Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.

Price vs latency

One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag

History

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 is OpenRouter's rolling 30-minute window.

Throughput

Median tokens per second.