Alibaba

60 endpoints · 3 unhealthy · worst uptime 76.86%

	State
DeepSeek V4.1 Flashalibaba	Healthy	100%	99.48%	98.36%	99.08%	1.32s	13.0s	74 tps	1.0M	$0.300 / $1.20
Qwen3 30B A3Balibaba	Healthy	100%	99.77%	99.85%	99.93%	479ms	4.00s	102 tps	131K	$0.130 / $0.520
Qwen3 8Balibaba	Healthy	100%	99.94%	99.76%	99.71%	601ms	1.13s	53 tps	131K	$0.117 / $0.455
Qwen3 Maxalibaba	Healthy	100%	99.76%	99.67%	99.88%	743ms	2.13s	52 tps	262K	$0.780 / $3.90
Qwen3 Max Thinkingalibaba	Healthy	100%	99.85%	99.91%	99.93%	811ms	2.05s	53 tps	262K	$0.780 / $3.90
Qwen3 Next 80B A3B Instructalibaba	Healthy	100%	99.79%	99.77%	99.91%	442ms	826ms	83 tps	131K	$0.098 / $0.780
Qwen3.5-27Balibaba	Healthy	100%	99.13%	98.15%	98.23%	788ms	37.0s	57 tps	262K	$0.195 / $1.56
Qwen3.5 397B A17Balibaba	Healthy	100%	99.83%	99.53%	99.75%	977ms	12.1s	100 tps	262K	$0.390 / $2.34
Qwen3.5 Plus 2026-02-15alibaba	Healthy	100%	99.75%	99.72%	99.87%	949ms	4.82s	55 tps	1.0M	$0.260 / $1.56
Qwen3.6 27Balibaba	Degraded	100%	95.14%	99.87%	99.92%	2.08s	32.1s	56 tps	262K	$0.450 / $2.70
Qwen3.6 Flashalibaba	Healthy	100%	99.95%	99.91%	99.97%	385ms	4.59s	115 tps	1.0M	$0.188 / $1.13
Qwen3.6 Plusalibaba	Healthy	100%	99.97%	99.92%	99.98%	972ms	17.9s	37 tps	1.0M	$0.325 / $1.95
Qwen3.7 Maxalibaba	Healthy	100%	99.97%	99.99%	99.99%	935ms	2.92s	84 tps	1.0M	$1.48 / $4.42
Qwen3.8 2.4T A95Balibaba	Healthy	100%	99.93%	99.91%	99.92%	1.48s	10.7s	38 tps	1.0M	$2.00 / $6.00
Qwen3.8 27Balibaba	Healthy	100%	99.63%	99.22%	99.56%	2.11s	55.0s	50 tps	1.0M	$0.425 / $2.55
Qwen3.8 Max Primealibaba	Healthy	100%	99.72%	99.55%	99.61%	951ms	5.64s	55 tps	1.0M	$4.00 / $12.00
GLM 5.1alibaba/fp8fp8	Healthy	100%	99.38%	96.90%	99.46%	1.20s	2.61s	87 tps	203K	$1.33 / $4.18
GLM 5.2alibaba/fastfp8	Healthy	100%	99.09%	99.67%	99.87%	1.16s	6.81s	98 tps	1.0M	$2.31 / $7.26
Qwen3.7 Flashalibaba	Healthy	99.97%	99.92%	99.93%	99.97%	609ms	5.14s	70 tps	1.0M	$0.030 / $0.130
Qwen3.7 Plusalibaba	Healthy	99.95%	99.88%	99.95%	99.97%	1.15s	7.71s	52 tps	1.0M	$0.320 / $1.28
Qwen3.5-Flashalibaba	Healthy	99.88%	99.83%	99.77%	99.90%	553ms	2.68s	83 tps	1.0M	$0.065 / $0.260
DeepSeek V4 Flash 0423alibaba/fp8fp8	Healthy	99.81%	99.16%	98.78%	99.09%	846ms	1.91s	113 tps	1.0M	$0.134 / $0.268
Qwen3.8 Max (0902)alibaba	Healthy	99.74%	99.78%	99.76%	99.82%	3.57s	65.6s	33 tps	1.0M	$2.00 / $6.00
Qwen3 VL 235B A22B Instructalibaba	Healthy	99.65%	99.40%	99.00%	99.43%	660ms	1.99s	42 tps	131K	$0.260 / $1.04
Qwen3.8 Omni Flashalibaba	Healthy	99.62%	98.97%	98.43%	98.58%	4.17s	70.9s	44 tps	1.0M	$0.150 / $0.470
Qwen3.8 Flashalibaba	Healthy	99.42%	98.69%	99.43%	99.77%	2.05s	11.1s	60 tps	1.0M	$0.150 / $0.470
Qwen3 30B A3B Instruct 2507alibaba	Healthy	99.40%	99.70%	99.59%	99.81%	300ms	1.22s	81 tps	131K	$0.130 / $0.520
Qwen3 VL 30B A3B Instructalibaba	Healthy	99.39%	99.30%	99.39%	99.75%	488ms	2.01s	59 tps	131K	$0.130 / $0.520
DeepSeek V4 Pro 0813alibaba	Healthy	99.37%	97.47%	98.09%	99.29%	1.08s	2.22s	76 tps	1.0M	$1.12 / $3.37
Qwen3 VL 8B Instructalibaba	Healthy	99.29%	99.49%	99.19%	99.69%	376ms	2.01s	82 tps	131K	$0.117 / $0.455
Qwen3 235B A22B Instruct 2507alibaba	Healthy	99.21%	98.67%	97.67%	99.01%	494ms	8.59s	54 tps	131K	$0.150 / $0.598
GLM 5.3 Primealibaba	Healthy	98.99%	99.41%	99.19%	99.18%	1.95s	13.8s	62 tps	1.0M	$2.80 / $8.80
Qwen3 VL 32B Instructalibaba	Healthy	98.55%	98.99%	99.24%	99.78%	703ms	49.2s	65 tps	131K	$0.104 / $0.416
GLM 5.2alibaba/fp8fp8	Healthy	98.52%	99.21%	98.85%	99.45%	902ms	15.8s	71 tps	1.0M	$0.966 / $3.04
DeepSeek V4 Flash 0731alibaba	Healthy	98.43%	99.07%	99.08%	99.63%	1.26s	6.94s	90 tps	1.0M	$0.352 / $1.06
Qwen3 235B A22Balibaba	Degraded	95.77%	98.40%	95.68%	98.34%	503ms	4.87s	52 tps	131K	$0.455 / $1.82
DeepSeek V4 Pro 0423alibaba/fp8fp8	Healthy	95.28%	87.19%	96.23%	98.66%	1.93s	3.05s	52 tps	1.0M	$1.42 / $2.83
DeepSeek V3.2alibaba/fp8fp8	Down	76.86%	90.71%	91.54%	96.70%	683ms	10.7s	42 tps	131K	$0.370 / $1.11
Kimi K2.7 Codealibaba/fp8fp8	No data	—	96.20%	98.69%	99.57%	1.77s	6.03s	53 tps	262K	$0.950 / $4.00
Kimi K3alibaba	No data	—	99.08%	99.05%	98.94%	1.46s	8.14s	51 tps	1.0M	$3.45 / $17.25
Qwen-Plusalibaba	No data	—	98.87%	98.27%	99.38%	387ms	1.56s	49 tps	1.0M	$0.260 / $0.780
Qwen Plus 0728alibaba	No data	—	99.91%	99.59%	99.90%	323ms	2.32s	67 tps	1.0M	$0.260 / $0.780
Qwen3 14Balibaba	No data	—	99.97%	99.51%	99.80%	220ms	3.69s	66 tps	131K	$0.227 / $0.910
Qwen3 235B A22B Thinking 2507alibaba	No data	—	99.30%	99.63%	99.84%	816ms	16.0s	64 tps	131K	$0.230 / $2.30
Qwen3 30B A3B Thinking 2507alibaba	No data	—	99.88%	99.84%	99.64%	295ms	1.07s	132 tps	82K	$0.200 / $2.40
Qwen3 Coder 480B A35Balibaba/opensource	No data	—	100%	99.96%	99.74%	1.00s	1.37s	47 tps	262K	$0.975 / $4.88
Qwen3 Coder 30B A3B Instructalibaba	No data	—	100%	99.99%	99.99%	871ms	5.54s	52 tps	262K	$0.292 / $1.46
Qwen3 Coder Flashalibaba	No data	—	99.96%	99.93%	99.95%	871ms	3.92s	75 tps	1.0M	$0.195 / $0.975
Qwen3 Coder Nextalibaba	No data	—	98.42%	99.55%	99.14%	933ms	1.34s	99 tps	262K	$0.300 / $1.50
Qwen3 Coder Plusalibaba	No data	—	100%	99.99%	99.99%	1.43s	4.66s	31 tps	1.0M	$0.650 / $3.25
Qwen3 Next 80B A3B Thinkingalibaba	No data	—	99.89%	99.99%	100%	442ms	970ms	176 tps	131K	$0.150 / $1.20
Qwen3 VL 235B A22B Thinkingalibaba	No data	—	89.90%	90.12%	92.47%	493ms	9.22s	57 tps	131K	$0.400 / $4.00
Qwen3 VL 30B A3B Thinkingalibaba	No data	—	99.96%	99.97%	99.99%	479ms	1.43s	108 tps	131K	$0.200 / $2.40
Qwen3 VL 8B Thinkingalibaba	No data	—	100%	99.94%	99.99%	419ms	758ms	121 tps	131K	$0.180 / $2.10
Qwen3.5-122B-A10Balibaba	No data	—	98.84%	97.46%	96.16%	493ms	7.73s	99 tps	262K	$0.260 / $2.08
Qwen3.5-35B-A3Balibaba	No data	—	92.01%	95.77%	96.12%	632ms	4.11s	126 tps	262K	$0.163 / $1.30
Qwen3.5 Plus 2026-04-20alibaba	No data	—	99.86%	99.35%	99.80%	1.06s	6.98s	50 tps	1.0M	$0.300 / $1.80
Qwen3.6 Max Previewalibaba	No data	—	100%	99.97%	99.99%	934ms	2.04s	62 tps	262K	$1.03 / $6.16
GLM 5.3alibaba	No data	—	99.97%	99.95%	99.65%	1.03s	6.68s	74 tps	1.0M	$1.19 / $3.74
GLM 5.3alibaba/fast	No data	—	100%	100%	99.95%	—	—	—	1.0M	$2.80 / $8.80

DeepSeek V4.1 Flash100%
Healthy24h 99.48%
7d
98.36%
30d
99.08%
p50
1.32s
p99
13.0s
Throughput
74 tps
Context
1.0M
$/Mtok
$0.300 / $1.20
alibaba
Qwen3 30B A3B100%
Healthy24h 99.77%
7d
99.85%
30d
99.93%
p50
479ms
p99
4.00s
Throughput
102 tps
Context
131K
$/Mtok
$0.130 / $0.520
alibaba
Qwen3 8B100%
Healthy24h 99.94%
7d
99.76%
30d
99.71%
p50
601ms
p99
1.13s
Throughput
53 tps
Context
131K
$/Mtok
$0.117 / $0.455
alibaba
Qwen3 Max100%
Healthy24h 99.76%
7d
99.67%
30d
99.88%
p50
743ms
p99
2.13s
Throughput
52 tps
Context
262K
$/Mtok
$0.780 / $3.90
alibaba
Qwen3 Max Thinking100%
Healthy24h 99.85%
7d
99.91%
30d
99.93%
p50
811ms
p99
2.05s
Throughput
53 tps
Context
262K
$/Mtok
$0.780 / $3.90
alibaba
Qwen3 Next 80B A3B Instruct100%
Healthy24h 99.79%
7d
99.77%
30d
99.91%
p50
442ms
p99
826ms
Throughput
83 tps
Context
131K
$/Mtok
$0.098 / $0.780
alibaba
Qwen3.5-27B100%
Healthy24h 99.13%
7d
98.15%
30d
98.23%
p50
788ms
p99
37.0s
Throughput
57 tps
Context
262K
$/Mtok
$0.195 / $1.56
alibaba
Qwen3.5 397B A17B100%
Healthy24h 99.83%
7d
99.53%
30d
99.75%
p50
977ms
p99
12.1s
Throughput
100 tps
Context
262K
$/Mtok
$0.390 / $2.34
alibaba
Qwen3.5 Plus 2026-02-15100%
Healthy24h 99.75%
7d
99.72%
30d
99.87%
p50
949ms
p99
4.82s
Throughput
55 tps
Context
1.0M
$/Mtok
$0.260 / $1.56
alibaba
Qwen3.6 27B100%
Degraded24h 95.14%
7d
99.87%
30d
99.92%
p50
2.08s
p99
32.1s
Throughput
56 tps
Context
262K
$/Mtok
$0.450 / $2.70
alibaba
Qwen3.6 Flash100%
Healthy24h 99.95%
7d
99.91%
30d
99.97%
p50
385ms
p99
4.59s
Throughput
115 tps
Context
1.0M
$/Mtok
$0.188 / $1.13
alibaba
Qwen3.6 Plus100%
Healthy24h 99.97%
7d
99.92%
30d
99.98%
p50
972ms
p99
17.9s
Throughput
37 tps
Context
1.0M
$/Mtok
$0.325 / $1.95
alibaba
Qwen3.7 Max100%
Healthy24h 99.97%
7d
99.99%
30d
99.99%
p50
935ms
p99
2.92s
Throughput
84 tps
Context
1.0M
$/Mtok
$1.48 / $4.42
alibaba
Qwen3.8 2.4T A95B100%
Healthy24h 99.93%
7d
99.91%
30d
99.92%
p50
1.48s
p99
10.7s
Throughput
38 tps
Context
1.0M
$/Mtok
$2.00 / $6.00
alibaba
Qwen3.8 27B100%
Healthy24h 99.63%
7d
99.22%
30d
99.56%
p50
2.11s
p99
55.0s
Throughput
50 tps
Context
1.0M
$/Mtok
$0.425 / $2.55
alibaba
Qwen3.8 Max Prime100%
Healthy24h 99.72%
7d
99.55%
30d
99.61%
p50
951ms
p99
5.64s
Throughput
55 tps
Context
1.0M
$/Mtok
$4.00 / $12.00
alibaba
GLM 5.1100%
Healthy24h 99.38%
7d
96.90%
30d
99.46%
p50
1.20s
p99
2.61s
Throughput
87 tps
Context
203K
$/Mtok
$1.33 / $4.18
alibaba/fp8fp8
GLM 5.2100%
Healthy24h 99.09%
7d
99.67%
30d
99.87%
p50
1.16s
p99
6.81s
Throughput
98 tps
Context
1.0M
$/Mtok
$2.31 / $7.26
alibaba/fastfp8
Qwen3.7 Flash99.97%
Healthy24h 99.92%
7d
99.93%
30d
99.97%
p50
609ms
p99
5.14s
Throughput
70 tps
Context
1.0M
$/Mtok
$0.030 / $0.130
alibaba
Qwen3.7 Plus99.95%
Healthy24h 99.88%
7d
99.95%
30d
99.97%
p50
1.15s
p99
7.71s
Throughput
52 tps
Context
1.0M
$/Mtok
$0.320 / $1.28
alibaba
Qwen3.5-Flash99.88%
Healthy24h 99.83%
7d
99.77%
30d
99.90%
p50
553ms
p99
2.68s
Throughput
83 tps
Context
1.0M
$/Mtok
$0.065 / $0.260
alibaba
DeepSeek V4 Flash 042399.81%
Healthy24h 99.16%
7d
98.78%
30d
99.09%
p50
846ms
p99
1.91s
Throughput
113 tps
Context
1.0M
$/Mtok
$0.134 / $0.268
alibaba/fp8fp8
Qwen3.8 Max (0902)99.74%
Healthy24h 99.78%
7d
99.76%
30d
99.82%
p50
3.57s
p99
65.6s
Throughput
33 tps
Context
1.0M
$/Mtok
$2.00 / $6.00
alibaba
Qwen3 VL 235B A22B Instruct99.65%
Healthy24h 99.40%
7d
99.00%
30d
99.43%
p50
660ms
p99
1.99s
Throughput
42 tps
Context
131K
$/Mtok
$0.260 / $1.04
alibaba
Qwen3.8 Omni Flash99.62%
Healthy24h 98.97%
7d
98.43%
30d
98.58%
p50
4.17s
p99
70.9s
Throughput
44 tps
Context
1.0M
$/Mtok
$0.150 / $0.470
alibaba
Qwen3.8 Flash99.42%
Healthy24h 98.69%
7d
99.43%
30d
99.77%
p50
2.05s
p99
11.1s
Throughput
60 tps
Context
1.0M
$/Mtok
$0.150 / $0.470
alibaba
Qwen3 30B A3B Instruct 250799.40%
Healthy24h 99.70%
7d
99.59%
30d
99.81%
p50
300ms
p99
1.22s
Throughput
81 tps
Context
131K
$/Mtok
$0.130 / $0.520
alibaba
Qwen3 VL 30B A3B Instruct99.39%
Healthy24h 99.30%
7d
99.39%
30d
99.75%
p50
488ms
p99
2.01s
Throughput
59 tps
Context
131K
$/Mtok
$0.130 / $0.520
alibaba
DeepSeek V4 Pro 081399.37%
Healthy24h 97.47%
7d
98.09%
30d
99.29%
p50
1.08s
p99
2.22s
Throughput
76 tps
Context
1.0M
$/Mtok
$1.12 / $3.37
alibaba
Qwen3 VL 8B Instruct99.29%
Healthy24h 99.49%
7d
99.19%
30d
99.69%
p50
376ms
p99
2.01s
Throughput
82 tps
Context
131K
$/Mtok
$0.117 / $0.455
alibaba
Qwen3 235B A22B Instruct 250799.21%
Healthy24h 98.67%
7d
97.67%
30d
99.01%
p50
494ms
p99
8.59s
Throughput
54 tps
Context
131K
$/Mtok
$0.150 / $0.598
alibaba
GLM 5.3 Prime98.99%
Healthy24h 99.41%
7d
99.19%
30d
99.18%
p50
1.95s
p99
13.8s
Throughput
62 tps
Context
1.0M
$/Mtok
$2.80 / $8.80
alibaba
Qwen3 VL 32B Instruct98.55%
Healthy24h 98.99%
7d
99.24%
30d
99.78%
p50
703ms
p99
49.2s
Throughput
65 tps
Context
131K
$/Mtok
$0.104 / $0.416
alibaba
GLM 5.298.52%
Healthy24h 99.21%
7d
98.85%
30d
99.45%
p50
902ms
p99
15.8s
Throughput
71 tps
Context
1.0M
$/Mtok
$0.966 / $3.04
alibaba/fp8fp8
DeepSeek V4 Flash 073198.43%
Healthy24h 99.07%
7d
99.08%
30d
99.63%
p50
1.26s
p99
6.94s
Throughput
90 tps
Context
1.0M
$/Mtok
$0.352 / $1.06
alibaba
Qwen3 235B A22B95.77%
Degraded24h 98.40%
7d
95.68%
30d
98.34%
p50
503ms
p99
4.87s
Throughput
52 tps
Context
131K
$/Mtok
$0.455 / $1.82
alibaba
DeepSeek V4 Pro 042395.28%
Healthy24h 87.19%
7d
96.23%
30d
98.66%
p50
1.93s
p99
3.05s
Throughput
52 tps
Context
1.0M
$/Mtok
$1.42 / $2.83
alibaba/fp8fp8
DeepSeek V3.276.86%
Down24h 90.71%
7d
91.54%
30d
96.70%
p50
683ms
p99
10.7s
Throughput
42 tps
Context
131K
$/Mtok
$0.370 / $1.11
alibaba/fp8fp8
Kimi K2.7 Code—
No data24h 96.20%
7d
98.69%
30d
99.57%
p50
1.77s
p99
6.03s
Throughput
53 tps
Context
262K
$/Mtok
$0.950 / $4.00
alibaba/fp8fp8
Kimi K3—
No data24h 99.08%
7d
99.05%
30d
98.94%
p50
1.46s
p99
8.14s
Throughput
51 tps
Context
1.0M
$/Mtok
$3.45 / $17.25
alibaba
Qwen-Plus—
No data24h 98.87%
7d
98.27%
30d
99.38%
p50
387ms
p99
1.56s
Throughput
49 tps
Context
1.0M
$/Mtok
$0.260 / $0.780
alibaba
Qwen Plus 0728—
No data24h 99.91%
7d
99.59%
30d
99.90%
p50
323ms
p99
2.32s
Throughput
67 tps
Context
1.0M
$/Mtok
$0.260 / $0.780
alibaba
Qwen3 14B—
No data24h 99.97%
7d
99.51%
30d
99.80%
p50
220ms
p99
3.69s
Throughput
66 tps
Context
131K
$/Mtok
$0.227 / $0.910
alibaba
Qwen3 235B A22B Thinking 2507—
No data24h 99.30%
7d
99.63%
30d
99.84%
p50
816ms
p99
16.0s
Throughput
64 tps
Context
131K
$/Mtok
$0.230 / $2.30
alibaba
Qwen3 30B A3B Thinking 2507—
No data24h 99.88%
7d
99.84%
30d
99.64%
p50
295ms
p99
1.07s
Throughput
132 tps
Context
82K
$/Mtok
$0.200 / $2.40
alibaba
Qwen3 Coder 480B A35B—
No data24h 100%
7d
99.96%
30d
99.74%
p50
1.00s
p99
1.37s
Throughput
47 tps
Context
262K
$/Mtok
$0.975 / $4.88
alibaba/opensource
Qwen3 Coder 30B A3B Instruct—
No data24h 100%
7d
99.99%
30d
99.99%
p50
871ms
p99
5.54s
Throughput
52 tps
Context
262K
$/Mtok
$0.292 / $1.46
alibaba
Qwen3 Coder Flash—
No data24h 99.96%
7d
99.93%
30d
99.95%
p50
871ms
p99
3.92s
Throughput
75 tps
Context
1.0M
$/Mtok
$0.195 / $0.975
alibaba
Qwen3 Coder Next—
No data24h 98.42%
7d
99.55%
30d
99.14%
p50
933ms
p99
1.34s
Throughput
99 tps
Context
262K
$/Mtok
$0.300 / $1.50
alibaba
Qwen3 Coder Plus—
No data24h 100%
7d
99.99%
30d
99.99%
p50
1.43s
p99
4.66s
Throughput
31 tps
Context
1.0M
$/Mtok
$0.650 / $3.25
alibaba
Qwen3 Next 80B A3B Thinking—
No data24h 99.89%
7d
99.99%
30d
100%
p50
442ms
p99
970ms
Throughput
176 tps
Context
131K
$/Mtok
$0.150 / $1.20
alibaba
Qwen3 VL 235B A22B Thinking—
No data24h 89.90%
7d
90.12%
30d
92.47%
p50
493ms
p99
9.22s
Throughput
57 tps
Context
131K
$/Mtok
$0.400 / $4.00
alibaba
Qwen3 VL 30B A3B Thinking—
No data24h 99.96%
7d
99.97%
30d
99.99%
p50
479ms
p99
1.43s
Throughput
108 tps
Context
131K
$/Mtok
$0.200 / $2.40
alibaba
Qwen3 VL 8B Thinking—
No data24h 100%
7d
99.94%
30d
99.99%
p50
419ms
p99
758ms
Throughput
121 tps
Context
131K
$/Mtok
$0.180 / $2.10
alibaba
Qwen3.5-122B-A10B—
No data24h 98.84%
7d
97.46%
30d
96.16%
p50
493ms
p99
7.73s
Throughput
99 tps
Context
262K
$/Mtok
$0.260 / $2.08
alibaba
Qwen3.5-35B-A3B—
No data24h 92.01%
7d
95.77%
30d
96.12%
p50
632ms
p99
4.11s
Throughput
126 tps
Context
262K
$/Mtok
$0.163 / $1.30
alibaba
Qwen3.5 Plus 2026-04-20—
No data24h 99.86%
7d
99.35%
30d
99.80%
p50
1.06s
p99
6.98s
Throughput
50 tps
Context
1.0M
$/Mtok
$0.300 / $1.80
alibaba
Qwen3.6 Max Preview—
No data24h 100%
7d
99.97%
30d
99.99%
p50
934ms
p99
2.04s
Throughput
62 tps
Context
262K
$/Mtok
$1.03 / $6.16
alibaba
GLM 5.3—
No data24h 99.97%
7d
99.95%
30d
99.65%
p50
1.03s
p99
6.68s
Throughput
74 tps
Context
1.0M
$/Mtok
$1.19 / $3.74
alibaba
GLM 5.3—
No data24h 100%
7d
100%
30d
99.95%
p50
—
p99
—
Throughput
—
Context
1.0M
$/Mtok
$2.80 / $8.80
alibaba/fast