GMICloud

26 endpoints · 5 unhealthy · worst uptime 79.39%

	State
DeepSeek V4 Flash 0731gmicloud/fp8fp8	Healthy	100%	99.99%	99.97%	96.01%	1.73s	4.50s	73 tps	1.0M	$0.286 / $0.858
DeepSeek V4 Flash Vision Expgmicloud/fp8fp8	Healthy	100%	99.99%	99.88%	99.40%	3.34s	17.6s	77 tps	1.0M	$0.440 / $1.32
DeepSeek V4 Pro 0423gmicloud/fp8fp8	Healthy	100%	99.40%	99.41%	98.94%	2.71s	8.55s	25 tps	1.0M	$0.957 / $1.91
DeepSeek V4 Pro 0813gmicloud/fp8fp8	Healthy	100%	99.94%	99.94%	99.77%	3.67s	5.34s	31 tps	1.0M	$1.06 / $3.17
DeepSeek V4.1 Flashgmicloud/fp8fp8	Healthy	100%	99.57%	99.78%	99.30%	1.89s	16.7s	94 tps	1.0M	$0.180 / $0.720
MiniMax M2.7gmicloud/fp8fp8	Healthy	100%	99.61%	99.65%	99.41%	1.43s	28.5s	43 tps	197K	$0.210 / $0.840
MiniMax M3gmicloud/fp8fp8	Healthy	100%	99.49%	99.42%	99.50%	3.02s	10.8s	42 tps	1.0M	$0.240 / $0.960
Hy3 previewgmicloud/bf16bf16	Healthy	100%	100%	100%	100%	2.45s	15.5s	84 tps	262K	$0.180 / $0.600
MiMo-V2.6-Progmicloud/bf16bf16	Healthy	100%	99.27%	99.00%	98.99%	6.01s	46.3s	32 tps	1.1M	$0.435 / $0.870
GLM 5gmicloud/fp8fp8	Healthy	100%	98.96%	99.10%	98.48%	2.93s	7.10s	49 tps	203K	$0.600 / $1.92
DeepSeek V4 Flash 0423gmicloud/fp8fp8	Healthy	100%	99.85%	99.97%	99.69%	1.49s	4.44s	57 tps	1.0M	$0.091 / $0.182
Qwen3 235B A22B Instruct 2507gmicloud/fp8fp8	Healthy	99.87%	99.17%	98.19%	98.53%	1.22s	30.2s	46 tps	262K	$0.087 / $0.350
DeepSeek V3 0324gmicloud/fp8fp8	Healthy	99.33%	99.46%	98.86%	98.04%	2.79s	6.11s	33 tps	128K	$0.290 / $1.14
GLM 5.3 Flashgmicloud/fp8fp8	Degraded	96.56%	95.33%	98.89%	98.69%	5.64s	47.2s	25 tps	1.0M	$0.090 / $0.300
MiMo-V2.6-Flashgmicloud/bf16bf16	Degraded	95.72%	87.22%	87.22%	87.22%	3.27s	8.82s	42 tps	1.1M	$0.140 / $0.280
MiMo-V2.5gmicloud/fp8fp8	Degraded	95.24%	92.94%	85.42%	84.20%	2.38s	8.66s	37 tps	1.1M	$0.119 / $0.238
MiMo-V2.5-Progmicloud/bf16bf16	Degraded	93.33%	92.44%	86.56%	85.47%	2.56s	6.29s	37 tps	1.1M	$0.304 / $0.609
DeepSeek V3.2gmicloud/fp8fp8	Down	79.39%	90.35%	92.50%	98.08%	1.45s	5.24s	37 tps	164K	$0.209 / $0.310
MiniMax M2.5gmicloud/fp8fp8	No data	—	97.50%	100%	100%	1.54s	2.70s	49 tps	197K	$0.300 / $1.20
Kimi K2.6gmicloud/fp8fp8	No data	—	—	64.07%	92.38%	—	—	—	262K	$0.855 / $3.60
Kimi K2.7 Codegmicloud/fp8fp8	No data	—	99.61%	99.95%	99.92%	3.68s	17.6s	70 tps	262K	$0.950 / $4.00
Qwen3.5 397B A17Bgmicloud/fp8fp8	No data	—	84.67%	88.49%	86.98%	1.79s	3.39s	88 tps	262K	$0.600 / $3.60
Hy3gmicloud/bf16bf16	No data	—	99.75%	99.17%	99.18%	2.43s	7.49s	74 tps	262K	$0.140 / $0.580
GLM 5.1gmicloud/fp8fp8	No data	—	99.73%	98.21%	99.16%	1.54s	13.7s	49 tps	203K	$1.40 / $4.40
GLM 5.2gmicloud/fp8fp8	No data	—	98.49%	99.72%	99.76%	1.99s	6.42s	33 tps	1.0M	$1.40 / $4.40
GLM 5.3gmicloud/fp8fp8	No data	—	99.23%	99.83%	99.33%	3.42s	10.6s	43 tps	1.0M	$0.980 / $3.08

DeepSeek V4 Flash 0731100%
Healthy24h 99.99%
7d
99.97%
30d
96.01%
p50
1.73s
p99
4.50s
Throughput
73 tps
Context
1.0M
$/Mtok
$0.286 / $0.858
gmicloud/fp8fp8
DeepSeek V4 Flash Vision Exp100%
Healthy24h 99.99%
7d
99.88%
30d
99.40%
p50
3.34s
p99
17.6s
Throughput
77 tps
Context
1.0M
$/Mtok
$0.440 / $1.32
gmicloud/fp8fp8
DeepSeek V4 Pro 0423100%
Healthy24h 99.40%
7d
99.41%
30d
98.94%
p50
2.71s
p99
8.55s
Throughput
25 tps
Context
1.0M
$/Mtok
$0.957 / $1.91
gmicloud/fp8fp8
DeepSeek V4 Pro 0813100%
Healthy24h 99.94%
7d
99.94%
30d
99.77%
p50
3.67s
p99
5.34s
Throughput
31 tps
Context
1.0M
$/Mtok
$1.06 / $3.17
gmicloud/fp8fp8
DeepSeek V4.1 Flash100%
Healthy24h 99.57%
7d
99.78%
30d
99.30%
p50
1.89s
p99
16.7s
Throughput
94 tps
Context
1.0M
$/Mtok
$0.180 / $0.720
gmicloud/fp8fp8
MiniMax M2.7100%
Healthy24h 99.61%
7d
99.65%
30d
99.41%
p50
1.43s
p99
28.5s
Throughput
43 tps
Context
197K
$/Mtok
$0.210 / $0.840
gmicloud/fp8fp8
MiniMax M3100%
Healthy24h 99.49%
7d
99.42%
30d
99.50%
p50
3.02s
p99
10.8s
Throughput
42 tps
Context
1.0M
$/Mtok
$0.240 / $0.960
gmicloud/fp8fp8
Hy3 preview100%
Healthy24h 100%
7d
100%
30d
100%
p50
2.45s
p99
15.5s
Throughput
84 tps
Context
262K
$/Mtok
$0.180 / $0.600
gmicloud/bf16bf16
MiMo-V2.6-Pro100%
Healthy24h 99.27%
7d
99.00%
30d
98.99%
p50
6.01s
p99
46.3s
Throughput
32 tps
Context
1.1M
$/Mtok
$0.435 / $0.870
gmicloud/bf16bf16
GLM 5100%
Healthy24h 98.96%
7d
99.10%
30d
98.48%
p50
2.93s
p99
7.10s
Throughput
49 tps
Context
203K
$/Mtok
$0.600 / $1.92
gmicloud/fp8fp8
DeepSeek V4 Flash 0423100%
Healthy24h 99.85%
7d
99.97%
30d
99.69%
p50
1.49s
p99
4.44s
Throughput
57 tps
Context
1.0M
$/Mtok
$0.091 / $0.182
gmicloud/fp8fp8
Qwen3 235B A22B Instruct 250799.87%
Healthy24h 99.17%
7d
98.19%
30d
98.53%
p50
1.22s
p99
30.2s
Throughput
46 tps
Context
262K
$/Mtok
$0.087 / $0.350
gmicloud/fp8fp8
DeepSeek V3 032499.33%
Healthy24h 99.46%
7d
98.86%
30d
98.04%
p50
2.79s
p99
6.11s
Throughput
33 tps
Context
128K
$/Mtok
$0.290 / $1.14
gmicloud/fp8fp8
GLM 5.3 Flash96.56%
Degraded24h 95.33%
7d
98.89%
30d
98.69%
p50
5.64s
p99
47.2s
Throughput
25 tps
Context
1.0M
$/Mtok
$0.090 / $0.300
gmicloud/fp8fp8
MiMo-V2.6-Flash95.72%
Degraded24h 87.22%
7d
87.22%
30d
87.22%
p50
3.27s
p99
8.82s
Throughput
42 tps
Context
1.1M
$/Mtok
$0.140 / $0.280
gmicloud/bf16bf16
MiMo-V2.595.24%
Degraded24h 92.94%
7d
85.42%
30d
84.20%
p50
2.38s
p99
8.66s
Throughput
37 tps
Context
1.1M
$/Mtok
$0.119 / $0.238
gmicloud/fp8fp8
MiMo-V2.5-Pro93.33%
Degraded24h 92.44%
7d
86.56%
30d
85.47%
p50
2.56s
p99
6.29s
Throughput
37 tps
Context
1.1M
$/Mtok
$0.304 / $0.609
gmicloud/bf16bf16
DeepSeek V3.279.39%
Down24h 90.35%
7d
92.50%
30d
98.08%
p50
1.45s
p99
5.24s
Throughput
37 tps
Context
164K
$/Mtok
$0.209 / $0.310
gmicloud/fp8fp8
MiniMax M2.5—
No data24h 97.50%
7d
100%
30d
100%
p50
1.54s
p99
2.70s
Throughput
49 tps
Context
197K
$/Mtok
$0.300 / $1.20
gmicloud/fp8fp8
Kimi K2.6—
No data24h —
7d
64.07%
30d
92.38%
p50
—
p99
—
Throughput
—
Context
262K
$/Mtok
$0.855 / $3.60
gmicloud/fp8fp8
Kimi K2.7 Code—
No data24h 99.61%
7d
99.95%
30d
99.92%
p50
3.68s
p99
17.6s
Throughput
70 tps
Context
262K
$/Mtok
$0.950 / $4.00
gmicloud/fp8fp8
Qwen3.5 397B A17B—
No data24h 84.67%
7d
88.49%
30d
86.98%
p50
1.79s
p99
3.39s
Throughput
88 tps
Context
262K
$/Mtok
$0.600 / $3.60
gmicloud/fp8fp8
Hy3—
No data24h 99.75%
7d
99.17%
30d
99.18%
p50
2.43s
p99
7.49s
Throughput
74 tps
Context
262K
$/Mtok
$0.140 / $0.580
gmicloud/bf16bf16
GLM 5.1—
No data24h 99.73%
7d
98.21%
30d
99.16%
p50
1.54s
p99
13.7s
Throughput
49 tps
Context
203K
$/Mtok
$1.40 / $4.40
gmicloud/fp8fp8
GLM 5.2—
No data24h 98.49%
7d
99.72%
30d
99.76%
p50
1.99s
p99
6.42s
Throughput
33 tps
Context
1.0M
$/Mtok
$1.40 / $4.40
gmicloud/fp8fp8
GLM 5.3—
No data24h 99.23%
7d
99.83%
30d
99.33%
p50
3.42s
p99
10.6s
Throughput
43 tps
Context
1.0M
$/Mtok
$0.980 / $3.08
gmicloud/fp8fp8